© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 86459
    Prev
    Next
    INDEX
    Explanations

    team ranking

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    偎
    -0.08
     nouveaux
    -0.07
    אי
    -0.07
    第一百
    -0.07
     Jer
    -0.07
     Sure
    -0.07
     posts
    -0.07
    侧
    -0.07
    շ
    -0.07
     lav
    -0.07
    POSITIVE LOGITS
     NHL
    0.08
    .interfaces
    0.07
    OOK
    0.07
     Alumni
    0.07
    �
    0.07
     Staff
    0.06
    中国联通
    0.06
    .strategy
    0.06
    .sms
    0.06
    ornado
    0.06
    Activations Density 0.038%

    No Known Activations