© 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. 52440
    Prev
    Next
    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    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
    thin
    -0.07
    ('+
    -0.06
    trad
    -0.06
    _EXTERNAL
    -0.06
     Donne
    -0.06
     promot
    -0.06
     notion
    -0.06
    homme
    -0.06
    _foreign
    -0.06
    自主创新
    -0.06
    POSITIVE LOGITS
    伸手
    0.08
    ]["
    0.07
    \Schema
    0.07
    いただいた
    0.07
     sido
    0.07
    羽
    0.07
     surge
    0.07
    	fields
    0.07
    .accuracy
    0.07
    .Areas
    0.07
    Activations Density 0.096%

    No Known Activations