© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 107562
    Prev
    Next
    INDEX
    Explanations

    "there was" sentences

    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
    Negative Logits
    _ADAPTER
    -0.08
     */
    -0.07
    _backend
    -0.07
    ในฐานะ
    -0.06
     hayat
    -0.06
     closer
    -0.06
    VF
    -0.06
    不仅要
    -0.06
     został
    -0.06
     während
    -0.06
    POSITIVE LOGITS
    .Raise
    0.07
     giver
    0.07
    cych
    0.07
     spray
    0.07
    奪
    0.07
     spinach
    0.07
     spring
    0.06
    icho
    0.06
    进步
    0.06
    哟
    0.06
    Activations Density 0.066%

    No Known Activations