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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 15-RESID-POST-AA
    11. 76354
    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
    的功效
    -0.08
    ימות
    -0.08
     clientele
    -0.08
    奇纳河
    -0.07
    家门口
    -0.07
    淅
    -0.07
    惇
    -0.07
     spécifique
    -0.07
    häuser
    -0.07
    对付
    -0.06
    POSITIVE LOGITS
    )=>{↵
    0.07
    /mail
    0.07
    /,
    0.07
     Separate
    0.07
    DropDown
    0.07
    _EVAL
    0.07
    <header
    0.06
     Gap
    0.06
    /share
    0.06
     projected
    0.06
    Activations Density 0.015%

    No Known Activations