© 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. 42223
    Prev
    Next
    INDEX
    Explanations

    step within

    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
    æĿŁæīĭ
    -0.07
    æİĸ
    -0.07
    ª
    -0.07
    Spot
    -0.07
    ¯
    -0.07
    è¾Ħ
    -0.07
    æ´Ĺ涤åīĤ
    -0.07
    rieb
    -0.07
    spot
    -0.07
    abel
    -0.07
    POSITIVE LOGITS
     onset
    0.08
    éĥ½æĺ¯æľī
    0.07
    Past
    0.07
    ngo
    0.07
    åĴĮæľī
    0.07
    ogg
    0.07
    æĹŃ
    0.07
    åľ¨å²Ĺ
    0.07
    past
    0.07
    åIJ¯
    0.07
    Activations Density 0.002%

    No Known Activations