© 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. 92450
    Prev
    Next
    INDEX
    Explanations

    Comparing two 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
     Oversight
    -0.07
     الدولة
    -0.07
    شارك
    -0.06
    viron
    -0.06
     anticipating
    -0.06
    履
    -0.06
     ambition
    -0.06
     clicking
    -0.06
    son
    -0.06
    焕
    -0.06
    POSITIVE LOGITS
     true
    0.07
    (GL
    0.07
     {"
    0.06
    uml
    0.06
    ضح
    0.06
    =line
    0.06
    //#
    0.06
     lucrative
    0.06
    (channel
    0.06
    -----↵
    0.06
    Activations Density 0.064%

    No Known Activations