© 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. 12222
    Prev
    Next
    INDEX
    Explanations

    sunny

    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
    기업
    -0.07
    繇
    -0.07
    发文
    -0.07
    agu
    -0.07
     teh
    -0.07
    חיבור
    -0.07
     resembl
    -0.07
    悠久
    -0.06
    멓
    -0.06
     habe
    -0.06
    POSITIVE LOGITS
    .•
    0.07
    "}
    0.07
     Pall
    0.07
    信息系统
    0.06
     policies
    0.06
     Cum
    0.06
     ?.
    0.06
    לילה
    0.06
    合作关系
    0.06
    journal
    0.06
    Activations Density 0.015%

    No Known Activations