© 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. 43857
    Prev
    Next
    INDEX
    Explanations

    square classes

    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
    åĪĨéħį
    -0.07
    é¢Ĩ
    -0.06
    ene
    -0.06
    yn
    -0.06
    ил
    -0.06
    ka
    -0.06
     notwithstanding
    -0.06
    è¡Įäºij
    -0.06
    nn
    -0.06
     supplement
    -0.06
    POSITIVE LOGITS
    chend
    0.09
    ulah
    0.08
     Lá»ĩ
    0.08
     Sight
    0.08
    кÑĥлÑĮ
    0.07
    paralle
    0.07
    aub
    0.07
    ulta
    0.07
    稽
    0.07
    abschluss
    0.07
    Activations Density 0.005%

    No Known Activations