© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 45542
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    programming source-code snippets, particularly C/C++/Java-style code blocks with includes, function definitions, and brace-heavy syntax.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    	iNdEx
    -0.07
    imetype
    -0.07
    傲
    -0.07
    (requestCode
    -0.07
    /".$
    -0.07
    僇
    -0.07
    (isolate
    -0.07
     do
    -0.07
    (de
    -0.07
    总理
    -0.07
    POSITIVE LOGITS
     Munich
    0.07
    bullet
    0.07
     dar
    0.07
    排气
    0.07
     stationary
    0.07
     scalar
    0.07
    hal
    0.07
     what
    0.06
     FALSE
    0.06
     recher
    0.06
    Activations Density 0.041%

    No Known Activations