© 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. 50668
    Prev
    Next
    INDEX
    Explanations

    article

    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
    	pstmt
    -0.08
    躺在
    -0.08
    展厅
    -0.08
    تفسير
    -0.07
     Kurdish
    -0.07
    河流
    -0.07
    türk
    -0.07
    ԥ
    -0.07
     DropDownList
    -0.07
    Straight
    -0.07
    POSITIVE LOGITS
    ":↵↵
    0.07
    .au
    0.07
     noticed
    0.06
    adox
    0.06
    세
    0.06
     observe
    0.06
    acid
    0.06
    jest
    0.06
    ↽
    0.06
    ------------------------------------------------------------------------------------------------
    0.06
    Activations Density 0.000%

    No Known Activations