© 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. 19-RESID-POST-AA
    11. 7687
    Prev
    Next
    INDEX
    Explanations

    and

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SON
    -0.07
     şekil
    -0.07
    ퟰ
    -0.07
    	Code
    -0.06
    ords
    -0.06
    -tags
    -0.06
    olation
    -0.06
    ts
    -0.06
    亸
    -0.06
    atz
    -0.06
    POSITIVE LOGITS
     DISCLAIMED
    0.08
     Esc
    0.07
    FRINGEMENT
    0.07
    Apple
    0.07
    ⨍
    0.07
     spent
    0.07
     Kit
    0.07
     sized
    0.07
     Plugins
    0.07
    ◔
    0.07
    Activations Density 0.061%

    No Known Activations