© 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. 8758
    Prev
    Next
    INDEX
    Explanations

    computers and peripherals

    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
    —the
    -0.07
    —and
    -0.07
    —a
    -0.07
     inconsistent
    -0.06
    —or
    -0.06
    éĢ¼
    -0.06
    ibia
    -0.06
    enin
    -0.06
    abby
    -0.06
    év
    -0.06
    POSITIVE LOGITS
     etc
    0.12
    çŃīéĥ½æĺ¯
    0.12
    ä¹Łå¥½
    0.11
    çŃīåĿĩ
    0.11
    çŃīéĥ½
    0.11
    çŃīåľ¨
    0.10
     infatti
    0.10
    ä¹Łç½¢
    0.10
    çŃīè¿Ľè¡Į
    0.10
    åijĹ
    0.10
    Activations Density 0.121%

    No Known Activations