© 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. 26137
    Prev
    Next
    INDEX
    Explanations

    punctuation and symbols

    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
    ?,?,?,?,
    -0.09
    ä½Ĩä¸įéĻIJäºİ
    -0.07
    agara
    -0.07
    á»ĩt
    -0.07
    \\.
    -0.07
    burger
    -0.07
    ãĢģãĢģãĢģ
    -0.07
    lsi
    -0.06
    arien
    -0.06
    æ¡£æ¡Īé¦Ĩ
    -0.06
    POSITIVE LOGITS
    ope
    0.07
    çĸ«æĥħéĺ²æݧåĴĮ
    0.07
    mts
    0.07
    è§Ħ模åĴĮ
    0.07
    æ´ªæµģ
    0.06
    ä¸ŃåĽ½åĴĮ
    0.06
    idth
    0.06
    æľįåĬ¡åĴĮ
    0.06
    移åĬ¨çīĪ
    0.06
    æݧåĪ¶åĴĮ
    0.06
    Activations Density 0.094%

    No Known Activations