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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 23-RESID-POST-AA
    6. 320
    Prev
    Next
    INDEX
    Explanations

    evidence

    np_max-act-logits · gemini-2.0-flash
    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
    cuts
    -0.08
    reatment
    -0.07
    recio
    -0.07
    是一项
    -0.07
    attributes
    -0.07
    uden
    -0.07
     Numeric
    -0.07
    슭
    -0.07
    常见的
    -0.06
    小巧
    -0.06
    POSITIVE LOGITS
    ℍ
    0.07
    />↵
    0.07
    囫
    0.07
    ﹁
    0.06
     attrib
    0.06
     mín
    0.06
     incompatible
    0.06
     Iranians
    0.06
     chall
    0.06
    Ḡ
    0.06
    Activations Density 0.003%

    No Known Activations