© 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. 42125
    Prev
    Next
    INDEX
    Explanations

    tracebacks and errors

    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
    -toggler
    -0.09
    æľ¬ç«ĻåĨħ容
    -0.08
    _intf
    -0.08
    åĺ´è¾¹
    -0.07
    OPTION
    -0.07
    naval
    -0.07
    smarty
    -0.07
    æĤ¨å½ĵåīįçļĦä½įç½®
    -0.07
    nullptr
    -0.07
    ragen
    -0.07
    POSITIVE LOGITS
    ç²Ĵ
    0.07
     fatal
    0.06
    0.06
     Fatal
    0.06
    pre
    0.06
    anch
    0.06
    è½½
    0.06
     pras
    0.06
    ep
    0.05
     pre
    0.05
    Activations Density 0.059%

    No Known Activations