© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 20525
    Prev
    Next
    INDEX
    Explanations

    finger-related actions and body parts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     damn
    -0.08
    ains
    -0.07
    sein
    -0.07
     damned
    -0.07
    -fashioned
    -0.07
    ÙĬÙĪÙĨ
    -0.07
     Damn
    -0.07
    ãĥ¼ãĤŃ
    -0.07
    axter
    -0.07
    imers
    -0.07
    POSITIVE LOGITS
    /thumb
    0.11
    arro
    0.08
    occhio
    0.08
    PROPERTY
    0.08
    dal
    0.08
    ayat
    0.08
    ognito
    0.08
    à¸Ķย
    0.07
    çħ¤çģ°
    0.07
    Ī
    0.07
    Activations Density 0.020%

    No Known Activations