© 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. 33621
    Prev
    Next
    INDEX
    Explanations

    helper classes, functions, routines

    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
    座
    -0.06
     approaching
    -0.06
    etni
    -0.06
    æĺ¥æļĸ
    -0.06
     obv
    -0.06
    æķĪæŀľæĽ´å¥½
    -0.06
    åĬłå¼ºåŃ¦ä¹ł
    -0.06
    åĭĥåĭĥ
    -0.06
    .binding
    -0.06
    æĹ
    -0.05
    POSITIVE LOGITS
    heimer
    0.09
    rz
    0.09
    /Library
    0.08
    ög
    0.08
    estet
    0.08
    pcs
    0.08
    anken
    0.08
    intl
    0.08
    stvÃŃ
    0.08
    trin
    0.08
    Activations Density 0.001%

    No Known Activations