© 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. 10284
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and text

    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
    unken
    -0.07
    ault
    -0.07
    issan
    -0.07
    prak
    -0.07
    vend
    -0.07
    å¦
    -0.06
     voices
    -0.06
    çIJĨå·¥åѦéĻ¢
    -0.06
    _subset
    -0.06
     voix
    -0.06
    POSITIVE LOGITS
    çŁ¢éĩı
    0.07
    æĢ»é¢Ŀ为
    0.07
    çĹĽçļĦ
    0.07
    缸åħ³éĹ®çŃĶ
    0.07
    ົ
    0.07
    legung
    0.07
    agra
    0.07
     vectors
    0.07
    æĹłçŁ¥
    0.07
    è®°å½ķçļĦ
    0.07
    Activations Density 0.002%

    No Known Activations