© 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. 19131
    Prev
    Next
    INDEX
    Explanations

    endings for suffixes or code identifiers

    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
    ReadStream
    -0.07
    ิà¸Ī
    -0.07
    è¿ĽæĿ¥
    -0.07
    ril
    -0.07
    trys
    -0.06
    byname
    -0.06
     Mud
    -0.06
    mun
    -0.06
    SID
    -0.06
    ancis
    -0.06
    POSITIVE LOGITS
    ãģĤãĤĭãģĦãģ¯
    0.07
    ãĤĤãģĹãģıãģ¯
    0.07
    æĪĸä¸İ
    0.07
     Ðĺли
    0.07
    (or
    0.07
     íĺ¹ìĿĢ
    0.07
    или
    0.07
    resher
    0.07
     Oder
    0.07
    andom
    0.07
    Activations Density 0.117%

    No Known Activations