© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 22857
    Prev
    Next
    INDEX
    Explanations

    book reviews or listings

    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
    ãģĺãĤĵ
    -0.08
    ׼×ķף
    -0.08
    ĺ
    -0.08
    ments
    -0.08
    uky
    -0.08
    à¸ģารà¸ĵà¹Į
    -0.07
    occhi
    -0.07
    ients
    -0.07
    åĩ°
    -0.07
    ehu
    -0.07
    POSITIVE LOGITS
    keeping
    0.10
    edly
    0.10
    keeper
    0.09
    worm
    0.09
    shelf
    0.09
     pháºŃn
    0.08
    à¹Ģà¸Ľà¸¥à¹Īา
    0.08
    azine
    0.08
    holder
    0.08
    ILD
    0.08
    Activations Density 0.065%

    No Known Activations