© 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. 38955
    Prev
    Next
    INDEX
    Explanations

    special characters and punctuation

    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
    cito
    -0.08
    ĮĢ
    -0.08
    大åĪĢ
    -0.07
     ($(
    -0.07
    æľĪçĶŁ
    -0.07
    第ä¸īæī¹
    -0.07
    åľ¨çº¿çķĻè¨Ģ
    -0.07
    \xc
    -0.07
    身ä¸Ĭä¸ĭ
    -0.07
    åį°ç¬¬
    -0.07
    POSITIVE LOGITS
    ryn
    0.07
    lese
    0.07
    以ä¸Ĭ
    0.07
    azion
    0.07
    0.07
    è¡
    0.06
    reek
    0.06
    inality
    0.06
    akra
    0.06
    enix
    0.06
    Activations Density 0.125%

    No Known Activations