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. 11-RESID-POST-AA
    6. 92432
    Prev
    Next
    INDEX
    Explanations

    Pyralidae classification

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    蚧
    -0.07
    挖掘机
    -0.07
     bull
    -0.07
    大哥
    -0.07
    阀门
    -0.07
    血液
    -0.07
    _EM
    -0.07
    做到
    -0.06
    anch
    -0.06
     cutter
    -0.06
    POSITIVE LOGITS
     Rencontres
    0.08
    PERSON
    0.07
     Desc
    0.07
    vrier
    0.07
    𝐤
    0.07
    .IsNullOrWhiteSpace
    0.06
    othy
    0.06
     Yugosl
    0.06
    嶝
    0.06
     Those
    0.06
    Activations Density 0.037%

    No Known Activations