© 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. 84042
    Prev
    Next
    INDEX
    Explanations

    cereal

    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
    ='".$_
    -0.07
     '".$_
    -0.07
    =find
    -0.07
    所所
    -0.07
    _perms
    -0.07
    -find
    -0.07
    enqueue
    -0.07
    หนาว
    -0.07
    _once
    -0.07
     ],↵
    -0.07
    POSITIVE LOGITS
    괙
    0.07
    هواتف
    0.07
    自来水
    0.07
    aller
    0.07
    ल
    0.07
    społeczn
    0.06
    Verification
    0.06
    ve
    0.06
     hip
    0.06
     Colonial
    0.06
    Activations Density 0.001%

    No Known Activations