© 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. 43171
    Prev
    Next
    INDEX
    Explanations

    to parameters, data, or objectives

    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
    etty
    -0.08
    uelas
    -0.08
    ually
    -0.07
    iewicz
    -0.07
    legate
    -0.07
    noz
    -0.07
    wein
    -0.07
    egó
    -0.07
    /by
    -0.07
    æĺĵçĪĨ
    -0.07
    POSITIVE LOGITS
    oretical
    0.14
    orem
    0.12
    身临åħ¶å¢ĥ
    0.11
    oret
    0.11
    åĭĩå¾Ģ缴åīį
    0.10
    两åѦä¸Ģåģļ
    0.10
    ä¸įåı¯æĢĿè®®
    0.09
    odore
    0.08
    udas
    0.08
    èĢ³çĨŁèĥ½è¯¦
    0.08
    Activations Density 0.187%

    No Known Activations