© 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. 43686
    Prev
    Next
    INDEX
    Explanations

    JSON array or object structures

    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
    regon
    -0.06
    ìĬ¹
    -0.06
    OrDefault
    -0.06
    rad
    -0.06
    orus
    -0.06
     Gan
    -0.06
     Or
    -0.06
    éĩį
    -0.06
     S
    -0.06
    ä¸Ģæīĭ
    -0.06
    POSITIVE LOGITS
    hofer
    0.09
    LOPT
    0.08
    ITO
    0.08
    hower
    0.08
    ignment
    0.08
    lev
    0.08
    DONE
    0.08
    çļĦ大åѦ
    0.07
    ä½Ļç¯ĩ
    0.07
     verko
    0.07
    Activations Density 0.014%

    No Known Activations