© 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. 62596
    Prev
    Next
    INDEX
    Explanations

    master followed by noun

    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
    大潮
    -0.08
    æĪij社
    -0.08
    æ¦Ķ
    -0.08
    sett
    -0.08
    .Dot
    -0.08
    ixo
    -0.07
    ObjectType
    -0.07
    大åѦåĩºçīĪ社
    -0.07
    ãģ¾ãģĹãģ¦
    -0.07
    èĽī
    -0.07
    POSITIVE LOGITS
    liness
    0.09
    ized
    0.08
    ÑģÑĤвом
    0.08
    ÑģÑĤве
    0.08
    arial
    0.08
    rol
    0.08
    esco
    0.07
    ÑĪип
    0.07
    ica
    0.07
    izing
    0.07
    Activations Density 0.031%

    No Known Activations