© 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. 46053
    Prev
    Next
    INDEX
    Explanations

    game statistics or system setup

    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
    aglio
    -0.07
    å®ľäºº
    -0.07
    allon
    -0.07
    iglio
    -0.07
    æľªå¿ħ
    -0.07
    ä¸į论
    -0.06
    új
    -0.06
    åıĪ以
    -0.06
    éĺµ
    -0.06
    ück
    -0.06
    POSITIVE LOGITS
    ===========
    0.08
    loon
    0.08
    æľ¬åħ¬ä¼Ĺåı·
    0.07
    æĺ¯æŶåĢĻ
    0.07
    /testify
    0.07
    inama
    0.07
    noz
    0.07
    lest
    0.07
    ungi
    0.07
    estad
    0.07
    Activations Density 0.002%

    No Known Activations