© 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. 47595
    Prev
    Next
    INDEX
    Explanations

    dates ending in 00/06/14/15/16

    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
    ä¹Łç½¢
    -0.07
     abad
    -0.07
    ÑĢик
    -0.07
    åį³æĹ¥èµ·
    -0.07
    rary
    -0.07
    stellungs
    -0.07
    ä¸īåįĥ
    -0.06
    CHOOL
    -0.06
    enan
    -0.06
    åħ¬åħ±é¢Ħç®Ĺ
    -0.06
    POSITIVE LOGITS
    chetta
    0.08
    缸è¾ħ缸æĪIJ
    0.07
    �
    0.07
    iews
    0.07
    afka
    0.07
    -Jan
    0.07
    ī
    0.07
    днÑı
    0.07
    leans
    0.07
    agher
    0.07
    Activations Density 0.473%

    No Known Activations