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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 131023
    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
     Name
    -0.07
    坐下
    -0.07
     propTypes
    -0.07
     ensemble
    -0.06
     Vocal
    -0.06
    澳门
    -0.06
    }'.
    -0.06
     carbon
    -0.06
    长沙市
    -0.06
    全面
    -0.06
    POSITIVE LOGITS
     cuent
    0.08
    fifo
    0.07
     Middleware
    0.07
    willReturn
    0.07
    DCF
    0.07
    📲
    0.07
    邽
    0.07
    *
    ↵
    0.07
    Flags
    0.07
     currentState
    0.07
    Activations Density 0.014%

    No Known Activations