© 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. 19-RESID-POST-AA
    11. 96213
    Prev
    Next
    INDEX
    Explanations

    findings

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    附件
    -0.07
    toHaveBeenCalledWith
    -0.07
    Mgr
    -0.07
     concess
    -0.07
     информ
    -0.07
    糇
    -0.07
    捽
    -0.07
    _means
    -0.07
     confidential
    -0.07
     prepares
    -0.06
    POSITIVE LOGITS
    'll
    0.08
    FL
    0.07
    練
    0.07
    감
    0.07
     findings
    0.07
    Img
    0.07
     tumor
    0.07
    行星
    0.07
    SA
    0.07
     anomaly
    0.07
    Activations Density 0.013%

    No Known Activations