© 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. 24434
    Prev
    Next
    INDEX
    Explanations

    connect localhost

    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
    æľºæ¢°åĮĸ
    -0.07
    æĪij们èĩªå·±
    -0.06
    åĮºåĮº
    -0.06
    hints
    -0.06
    /compiler
    -0.06
    åĽ½åĨħå¸Ĥåľº
    -0.06
    itan
    -0.06
    ICS
    -0.06
    indle
    -0.06
    ç»Ļ对æĸ¹
    -0.06
    POSITIVE LOGITS
    èIJ¥åķĨ
    0.08
    å®Ĺ亲
    0.07
    odont
    0.07
    èĮĤ
    0.07
    ajan
    0.07
    jo
    0.07
    ajs
    0.07
    chau
    0.07
    æĵĩ
    0.07
    Ñħам
    0.07
    Activations Density 0.027%

    No Known Activations