© 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. 57926
    Prev
    Next
    INDEX
    Explanations

    monthly Chicago audio server c Hide

    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
    ½
    -0.08
    ending
    -0.06
    okia
    -0.06
    _conf
    -0.06
    op
    -0.06
    ände
    -0.06
    arring
    -0.06
    endus
    -0.06
    end
    -0.06
    Dur
    -0.06
    POSITIVE LOGITS
    æĸ°åħī
    0.08
    \\/
    0.08
    å¾Ĺ人
    0.07
    ä¸įåºĶæ±Ĥ
    0.07
    TTTT
    0.07
    ıntı
    0.07
    _sv
    0.07
    queued
    0.07
    vsp
    0.07
    ä¸ºä½łæıIJä¾Ľ
    0.07
    Activations Density 0.381%

    No Known Activations