© 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. 33356
    Prev
    Next
    INDEX
    Explanations

    input functions and class overrides

    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
     CORR
    -0.07
    updatedAt
    -0.07
    áŁĦ
    -0.07
    isNull
    -0.07
    å¦ĻçļĦ
    -0.07
    urch
    -0.07
    ä¸ĭåľº
    -0.07
    /fw
    -0.07
     ШÑĥ
    -0.07
    umpy
    -0.07
    POSITIVE LOGITS
     Sut
    0.07
    ä¸įå®Į
    0.06
     Tet
    0.06
    åijĽ
    0.06
    alh
    0.06
     pam
    0.06
    odu
    0.06
    ekret
    0.06
    ãĤĴãĤĪãģı
    0.06
    _dem
    0.05
    Activations Density 0.007%

    No Known Activations