© 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. 61583
    Prev
    Next
    INDEX
    Explanations

    file bench

    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
    åħĭæŀĹ
    -0.09
    itis
    -0.08
    iel
    -0.07
    еле
    -0.07
    iot
    -0.07
    ä¸įéļ¾çľĭåĩº
    -0.07
    åĭī
    -0.07
    çĽ¼
    -0.07
    Å¡em
    -0.07
    ç«łèĬĤéĶĻ误
    -0.07
    POSITIVE LOGITS
    ×ķ×ķת
    0.08
    濱
    0.07
     stringify
    0.07
    plied
    0.06
    вого
    0.06
    声åĵį
    0.06
    |string
    0.06
     FIXME
    0.06
    家å®Ŀ
    0.06
     Differential
    0.06
    Activations Density 0.378%

    No Known Activations