© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 129892
    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_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ouncement
    -0.07
    <Order
    -0.07
    (book
    -0.07
    っ
    -0.07
    男孩子
    -0.07
    ighest
    -0.06
     יצחק
    -0.06
     Manga
    -0.06
    blems
    -0.06
     Rune
    -0.06
    POSITIVE LOGITS
    NE
    0.07
    ?";↵
    0.07
     scheduler
    0.07
    每个
    0.07
     constructor
    0.06
    tmpl
    0.06
     nợ
    0.06
     Prefer
    0.06
    --------↵↵
    0.06
    constructor
    0.06
    Activations Density 0.000%

    No Known Activations