© 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. 129219
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
    ﺭ
    -0.07
     harassment
    -0.07
     넘어
    -0.07
     weary
    -0.07
     DISPATCH
    -0.07
    واجه
    -0.06
    icipant
    -0.06
     Fuel
    -0.06
     laundering
    -0.06
    enci
    -0.06
    POSITIVE LOGITS
     Eg
    0.08
    凼
    0.07
    ▊
    0.07
     Üniversitesi
    0.07
    .Dict
    0.07
    .TryParse
    0.07
    PointSize
    0.07
     JAXBElement
    0.07
    ++)↵
    0.06
    最大程度
    0.06
    Activations Density 0.017%

    No Known Activations