© 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. 128896
    Prev
    Next
    INDEX
    Explanations

    cost

    np_max-act · gemini-2.0-flash
    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
    第一步
    -0.07
     pn
    -0.07
    ở
    -0.07
    阅读
    -0.07
     Specifically
    -0.07
    ILED
    -0.07
    胯
    -0.07
    摞
    -0.07
    整
    -0.07
    =yes
    -0.06
    POSITIVE LOGITS
    orders
    0.08
    -Nazi
    0.07
    캐
    0.07
    عالم
    0.07
     analogy
    0.07
    쐐
    0.07
    贵宾
    0.06
    זמן
    0.06
    _requests
    0.06
    аз
    0.06
    Activations Density 0.019%

    No Known Activations