© 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. 58610
    Prev
    Next
    INDEX
    Explanations

    relief items

    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
    deaux
    -0.10
    ities
    -0.10
    eru
    -0.10
    endien
    -0.08
    eenth
    -0.08
    خاذ
    -0.08
    ungi
    -0.08
    cola
    -0.08
    igts
    -0.08
    ìĦ±ê¸ī
    -0.08
    POSITIVE LOGITS
    ़
    0.09
    ic
    0.08
    ä¸įå¼ĢçļĦ
    0.08
    èĢ¦
    0.08
    ed
    0.07
    igsaw
    0.07
    ਼
    0.07
    ÑģÑĤоÑĢон
    0.07
     Nobel
    0.07
    å¾ĢæľŁç²¾å½©
    0.07
    Activations Density 0.003%

    No Known Activations