© 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. 12605
    Prev
    Next
    INDEX
    Explanations

    Something stands in the way

    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
    de
    -0.07
    平安
    -0.06
    õ
    -0.06
    围棋
    -0.06
    aid
    -0.06
     geometric
    -0.06
     Conditional
    -0.06
     beat
    -0.06
     advises
    -0.06
     disasters
    -0.06
    POSITIVE LOGITS
    $file
    0.08
     Stub
    0.08
    connection
    0.08
    绯
    0.07
     Cah
    0.07
    חקירה
    0.07
     Rated
    0.07
    .Collection
    0.07
     Plumbing
    0.07
    Marks
    0.07
    Activations Density 0.032%

    No Known Activations