© 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. 47519
    Prev
    Next
    INDEX
    Explanations

    value, span, strength, level

    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
    åĽ¾çīĩæĪĸ
    -0.07
    üng
    -0.07
    -email
    -0.07
     prega
    -0.06
    åĻ
    -0.06
    éŨåı£çļĦ
    -0.06
    indy
    -0.06
    æ¿
    -0.06
     ür
    -0.06
    åħ«éĥ¨
    -0.06
    POSITIVE LOGITS
    ä¼ļè®®åı¬å¼Ģ
    0.08
    èįĨ
    0.08
     rose
    0.07
    ufa
    0.07
    peon
    0.07
    icie
    0.07
    æĢ»åĢ¼
    0.07
    å¸ĥæĸ¯
    0.06
    åĬĽæĮº
    0.06
    adu
    0.06
    Activations Density 0.044%

    No Known Activations