© 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. 7809
    Prev
    Next
    INDEX
    Explanations

    pedometer, cilium, Minerals, Cake, Chocolate, pump

    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
    ä»ħæѤ
    -0.10
    ллÑı
    -0.08
    æīĢèĥ½åıĬ
    -0.07
     ÐĶополни
    -0.07
    æīij
    -0.07
    ensuu
    -0.07
     Sipil
    -0.07
    ãĥ¼ãĤ¸ãĥ£
    -0.07
    ampton
    -0.07
    istik
    -0.07
    POSITIVE LOGITS
    ÑĤоÑĢи
    0.06
    /or
    0.06
    ､
    0.06
    ãĢģ
    0.06
    jent
    0.06
    uci
    0.06
    haven
    0.06
    arse
    0.05
    ux
    0.05
    bsites
    0.05
    Activations Density 1.339%

    No Known Activations