© 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. 30446
    Prev
    Next
    INDEX
    Explanations

    chi-square

    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
    ãģĦãĤĭ
    -0.08
    iates
    -0.08
    /off
    -0.07
    ional
    -0.07
    ehme
    -0.07
    chnik
    -0.07
    s
    -0.07
    ¸
    -0.06
    als
    -0.06
    ness
    -0.06
    POSITIVE LOGITS
    ameleon
    0.10
    avier
    0.10
    ecter
    0.09
    ÄĻc
    0.09
    jenigen
    0.09
    andra
    0.09
    osomal
    0.09
    大åı¯
    0.08
    °
    0.08
    buster
    0.08
    Activations Density 0.004%

    No Known Activations