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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11-RESID-POST-AA
    11. 34262
    Prev
    Next
    INDEX
    Explanations

    college

    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
     conservative
    -0.07
    戣
    -0.07
     replacements
    -0.07
     bash
    -0.07
     Jane
    -0.06
    Observers
    -0.06
    )=='
    -0.06
    endencies
    -0.06
     מו
    -0.06
    Cli
    -0.06
    POSITIVE LOGITS
    who
    0.07
    ⎣
    0.07
    檑
    0.07
     carousel
    0.07
     seeding
    0.06
    课
    0.06
    رون
    0.06
    蜂
    0.06
    _row
    0.06
    许多人
    0.06
    Activations Density 0.007%

    No Known Activations