© 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. 15772
    Prev
    Next
    INDEX
    Explanations

    stack trace or error reporting

    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
    ä¼ģä¸ļç®Ģä»ĭ
    -0.07
    rut
    -0.07
    åħ¬åı¸ç®Ģä»ĭ
    -0.07
    lays
    -0.07
    ice
    -0.06
     tro
    -0.06
    ç®Ģç«ł
    -0.06
    lay
    -0.06
     Tir
    -0.06
    unu
    -0.06
    POSITIVE LOGITS
    ัà¸Ļà¸Ĺ
    0.08
    ianto
    0.07
    дÑĥк
    0.07
    ooky
    0.07
    第äºĶ次
    0.07
    Õ¸ÖĢ
    0.07
    å°¼åħĭ
    0.07
    Ïīμα
    0.07
    SQ
    0.07
    debug
    0.07
    Activations Density 0.002%

    No Known Activations