© 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. 73203
    Prev
    Next
    INDEX
    Explanations

    HTML and foreign words

    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
    想过
    -0.08
    שמה
    -0.08
    庋
    -0.07
    ปลาย
    -0.07
     Belgi
    -0.07
    ᒌ
    -0.07
    تسويق
    -0.07
    wią
    -0.07
    ially
    -0.07
     ליצור
    -0.07
    POSITIVE LOGITS
     -----------
    0.07
     Nottingham
    0.07
     OE
    0.07
    占用
    0.07
     observation
    0.07
    .writerow
    0.07
    ɯ
    0.06
     X
    0.06
     Ir
    0.06
    准时
    0.06
    Activations Density 0.005%

    No Known Activations