© 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. 32619
    Prev
    Next
    INDEX
    Explanations

    time after specific events

    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
    éĻ
    -0.08
    ocup
    -0.08
    ailable
    -0.07
    æĺ¯ä¸įæĺ¯å¾Ī
    -0.07
     incluid
    -0.07
    otel
    -0.06
    以ä¸Ĭæĺ¯
    -0.06
    cms
    -0.06
    actly
    -0.06
    ruk
    -0.06
    POSITIVE LOGITS
     which
    0.13
    which
    0.12
     where
    0.11
     whereby
    0.11
     ØŃÙĬØ«
    0.10
     wherein
    0.10
     коÑĤоÑĢÑĭй
    0.10
     whose
    0.10
    where
    0.09
     коÑĤоÑĢаÑı
    0.09
    Activations Density 0.551%

    No Known Activations