© 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. 51624
    Prev
    Next
    INDEX
    Explanations

    square roots

    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
    åŃĺåľ¨ä¸ĢäºĽ
    -0.07
    ajib
    -0.07
    æĸ°åĬłåĿ¡
    -0.07
    VERR
    -0.07
    èĦļä¸ĭçļĦ
    -0.07
    ={({
    -0.07
    å´İå¸Ĥ
    -0.07
    _unused
    -0.07
    ubl
    -0.06
    ilon
    -0.06
    POSITIVE LOGITS
    ائرة
    0.07
    åĽ
    0.07
    loon
    0.06
    coma
    0.06
    ä»»ä½ķä¸ľè¥¿
    0.06
    abet
    0.06
    çĩ
    0.06
    åľ
    0.06
    èĮ«
    0.06
    adors
    0.06
    Activations Density 0.007%

    No Known Activations