© 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. 7-RESID-POST-AA
    11. 57174
    Prev
    Next
    INDEX
    Explanations

    palladium

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    文化和
    -0.09
    (pr
    -0.08
    _Draw
    -0.07
    ”↵
    -0.07
    ]:
↵
    -0.07
    凉
    -0.07
    (groups
    -0.07
     viet
    -0.07
    (inputs
    -0.07
     =>↵
    -0.07
    POSITIVE LOGITS
    Future
    0.07
    .Msg
    0.07
    ioni
    0.07
    师生
    0.07
    argout
    0.06
     Jesse
    0.06
    afi
    0.06
    .HttpStatus
    0.06
    棼
    0.06
     Porno
    0.06
    Activations Density 0.003%

    No Known Activations