© 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. 47265
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    ep
    -0.08
    è¯įæĿ¡
    -0.07
    utta
    -0.07
    elé
    -0.07
    hen
    -0.07
    tops
    -0.07
    KERNEL
    -0.07
    çĸij
    -0.07
    æł¸
    -0.07
    ele
    -0.06
    POSITIVE LOGITS
    /octet
    0.07
    æ°¸åĪ©
    0.07
    åĪĨ享åĪ°
    0.07
    è¯ºåŁº
    0.07
    arking
    0.07
    åĪ°æĪij
    0.06
     Smy
    0.06
    /downloads
    0.06
    éŨåħ³
    0.06
    åĪ°ä½ł
    0.06
    Activations Density 0.111%

    No Known Activations