© 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. 24485
    Prev
    Next
    INDEX
    Explanations

    raw data

    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
    à§Ģয়
    -0.08
    à¥įलà¥Ģ
    -0.08
    abler
    -0.08
    inux
    -0.08
    ary
    -0.08
    olia
    -0.08
    uido
    -0.08
    asley
    -0.08
    æIJľç´¢çĽ¸åħ³èµĦæĸĻ
    -0.07
    eday
    -0.07
    POSITIVE LOGITS
    urlencode
    0.10
    hide
    0.10
    ness
    0.09
    .githubusercontent
    0.09
    lings
    0.08
    天å°Ĭ
    0.08
    ุà¸Ķิà¸ļ
    0.07
    erty
    0.07
    ู
    0.07
    æĪĸéĥ¨åĪĨ
    0.07
    Activations Density 0.037%

    No Known Activations