© 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. 22348
    Prev
    Next
    INDEX
    Explanations

    PC, ME, X, An, NYSE company names

    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
    è¶Ĭæĥ³
    -0.09
    RowIndex
    -0.08
    anzo
    -0.07
    ancar
    -0.07
    åĬªåĬĽå·¥ä½ľ
    -0.07
    ä¼ļæľīä¸Ģ个
    -0.07
    -spot
    -0.07
    çľĭä¸įè§ģ
    -0.07
     Hardcover
    -0.07
    boh
    -0.07
    POSITIVE LOGITS
    ç®Ģ称
    0.14
    ä¸ĭ称
    0.11
    以ä¸ĭç®Ģ称
    0.11
    åıĪ称
    0.10
    簡稱
    0.09
    åıĪåIJį
    0.08
    aka
    0.07
    ä¹Łç§°
    0.07
    æĺµç§°
    0.07
     now
    0.07
    Activations Density 0.551%

    No Known Activations