© 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. 40053
    Prev
    Next
    INDEX
    Explanations

    punctuation and quotation marks

    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
    perm
    -0.08
    个人认为
    -0.07
    çŃīçĿĢä½ł
    -0.07
    åѤç«ĭ
    -0.07
    å¸ĮæľĽå¤§å®¶èĥ½å¤Ł
    -0.07
    说ä¸Ģä¸ĭ
    -0.07
    çľĭä¸Ģçľĭ
    -0.07
    .perm
    -0.07
    æĪij个人
    -0.07
    ç¾ģ
    -0.07
    POSITIVE LOGITS
    cplusplus
    0.08
    解éĩĬ说
    0.08
    æĺķ
    0.08
    uah
    0.08
    ä¸įåĢ¦
    0.08
    çľĭæĿ¥
    0.07
    IBE
    0.07
    ward
    0.07
    UY
    0.07
    ikian
    0.07
    Activations Density 0.067%

    No Known Activations