© 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. 38304
    Prev
    Next
    INDEX
    Explanations

    Copyright or file header

    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
    smith
    -0.08
    istiche
    -0.08
    ós
    -0.08
    opes
    -0.07
    åĪ¶éĢłå·¥èīº
    -0.07
    antina
    -0.07
    orph
    -0.07
    çĻ»è®°æīĭç»Ń
    -0.07
    imesteps
    -0.07
    zinho
    -0.07
    POSITIVE LOGITS
    ept
    0.07
    >>>>>>>
    0.07
    æĹĹä¸ĭ
    0.07
    jun
    0.07
     exped
    0.07
    èħ¹é»ij
    0.07
    ä¸ī家
    0.07
    yar
    0.06
    åĨĢ
    0.06
    å°ıå®Ŀ
    0.06
    Activations Density 0.002%

    No Known Activations