© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 60186
    Prev
    Next
    INDEX
    Explanations

    homo zy, sto ichi

    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
    sWith
    -0.10
    kannya
    -0.09
    ¦
    -0.09
    pun
    -0.08
    erman
    -0.08
    s
    -0.08
    à¸Ļà¹īà¸Ńย
    -0.07
    som
    -0.07
    spur
    -0.07
    à¸Ļา
    -0.07
    POSITIVE LOGITS
    htub
    0.09
    <|box_end|>
    0.08
    Ùĭ
    0.08
    ption
    0.08
    ä¸ŃæŬ
    0.08
    quee
    0.07
    itional
    0.07
    ist
    0.07
    elj
    0.07
    å©ķ
    0.06
    Activations Density 0.010%

    No Known Activations