© 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. 43891
    Prev
    Next
    INDEX
    Explanations

    programming keywords and syntax

    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
    fov
    -0.08
    मान
    -0.08
    unami
    -0.08
    è·»
    -0.07
    oš
    -0.07
    å·§
    -0.07
     Galler
    -0.07
    mania
    -0.07
    追尾
    -0.07
    /wp
    -0.07
    POSITIVE LOGITS
     Th
    0.07
    ä»ħä»£è¡¨ä½ľèĢħ
    0.07
    kens
    0.07
    _THROW
    0.06
    éĵľ
    0.06
    °
    0.06
    taki
    0.06
    ritz
    0.06
    ãĥ©ãĥ³ãĤ¹
    0.06
     chiamate
    0.06
    Activations Density 0.002%

    No Known Activations