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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 19-RESID-POST-AA
    6. 129463
    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_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
    Not in Any Lists

    No Comments

    Negative Logits
    아버지
    -0.08
    สถา
    -0.07
    lx
    -0.07
    肼
    -0.07
    尼克
    -0.06
    데
    -0.06
     מדוע
    -0.06
    比特
    -0.06
    通り
    -0.06
     pn
    -0.06
    POSITIVE LOGITS
     DRIVER
    0.07
    /MPL
    0.07
    ⠩
    0.07
     eighteen
    0.07
    (gray
    0.06
    _changes
    0.06
    >Returns
    0.06
    _ax
    0.06
    emale
    0.06
    +=(
    0.06
    Activations Density 0.002%

    No Known Activations