© 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. 11-RESID-POST-AA
    11. 62340
    Prev
    Next
    INDEX
    Explanations

    commas

    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
    _CAPACITY
    -0.08
    egie
    -0.07
    lüğü
    -0.07
    ✴
    -0.07
    _barrier
    -0.07
    漫长的
    -0.07
    uelle
    -0.07
    滋味
    -0.07
    Cross
    -0.07
    触发
    -0.06
    POSITIVE LOGITS
     forex
    0.07
    "So
    0.07
     '');↵↵
    0.07
    ,,
    0.07
    يرا
    0.07
    🐢
    0.06
    .print
    0.06
    (inputStream
    0.06
    ا
    0.06
     readme
    0.06
    Activations Density 0.009%

    No Known Activations