© 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. 28667
    Prev
    Next
    INDEX
    Explanations

    numbers and specific words like electron, boson, spin

    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
    åĹ
    -0.08
    åŁºæľ¬
    -0.07
    evol
    -0.07
    æľīæĿ¡ä»¶çļĦ
    -0.07
    æł©
    -0.07
    _ACL
    -0.07
    lips
    -0.07
    leps
    -0.07
    emies
    -0.07
    _BASIC
    -0.07
    POSITIVE LOGITS
    odd
    0.07
    çī©æµģæľįåĬ¡
    0.06
    à¸Ĺัà¹īà¸ĩà¸Ħูà¹Ī
    0.06
    oda
    0.06
    anyol
    0.06
    åģ¶
    0.06
    feuer
    0.06
    è´¹åĬĽ
    0.06
    çģ«èħ¿
    0.06
    apsed
    0.06
    Activations Density 0.001%

    No Known Activations