© 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. 32950
    Prev
    Next
    INDEX
    Explanations

    Comparing things

    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
    intval
    -0.07
    OfYear
    -0.07
    imeters
    -0.07
     Regina
    -0.07
     sein
    -0.07
    unteers
    -0.07
    .FILES
    -0.07
    Provides
    -0.07
     estos
    -0.07
     divers
    -0.06
    POSITIVE LOGITS
    .Mult
    0.07
     reasonable
    0.07
    Clearly
    0.07
     challenger
    0.06
    )>↵
    0.06
     failing
    0.06
     совершен
    0.06
     Sn
    0.06
     공
    0.06
    𝙙
    0.06
    Activations Density 0.006%

    No Known Activations