Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 75722
    Prev
    Next
    INDEX
    Explanations

    developed

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    עיתונ
    -0.07
    .lex
    -0.07
     phấn
    -0.07
     ideal
    -0.07
    .Local
    -0.07
    	nodes
    -0.07
    gänge
    -0.07
    \Image
    -0.06
    (parser
    -0.06
    .pk
    -0.06
    POSITIVE LOGITS
    本身的
    0.06
     interceptions
    0.06
     approach
    0.06
     strm
    0.06
     OnCollision
    0.06
    另一种
    0.06
    erties
    0.06
     fastest
    0.06
    ensed
    0.06
     shortest
    0.06
    Activations Density 0.049%

    No Known Activations