© 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. 3984
    Prev
    Next
    INDEX
    Explanations

    lists and 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
    详ç»ĨäºĨ解
    -0.06
     elif
    -0.06
     even
    -0.06
    殿
    -0.06
     superf
    -0.06
    idet
    -0.06
    impa
    -0.06
    ubat
    -0.06
    ibar
    -0.06
    åĩłä¹İæĺ¯
    -0.06
    POSITIVE LOGITS
    çŃīçŃī
    0.08
    ongan
    0.07
    anos
    0.07
    awas
    0.07
    azines
    0.07
    zcz
    0.07
    uard
    0.07
    hta
    0.07
    ä¿¡æģ¯çŃī
    0.07
    缸åħ³æݨèįIJ
    0.07
    Activations Density 0.167%

    No Known Activations