Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 76518
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cos
    -0.07
    queryParams
    -0.07
     connexion
    -0.07
    _representation
    -0.07
    🐸
    -0.07
    려
    -0.07
    .to
    -0.07
     classNames
    -0.07
    ApiClient
    -0.07
     Origin
    -0.07
    POSITIVE LOGITS
     EMPTY
    0.07
    嫭
    0.07
    횐
    0.07
    闲置
    0.07
     FIFO
    0.07
    纂
    0.07
     mük
    0.06
    �
    0.06
     �
    0.06
     SHORT
    0.06
    Activations Density 0.001%

    No Known Activations