© 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. 21372
    Prev
    Next
    INDEX
    Explanations

    to or not to

    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
    closest
    -0.07
     closest
    -0.07
    otics
    -0.07
    æĢİä¹Īèĥ½
    -0.06
    гÑĢом
    -0.06
    漪
    -0.06
    _CE
    -0.06
    chau
    -0.06
    perms
    -0.06
    adou
    -0.06
    POSITIVE LOGITS
    究竣æĺ¯
    0.17
     depending
    0.15
     versus
    0.15
    åĪ°åºķæĺ¯
    0.15
     vs
    0.15
    depending
    0.14
    åĨ³å®ļæĺ¯åIJ¦
    0.13
    究竣
    0.13
    è¿Ļ两ç§į
    0.13
     Depending
    0.12
    Activations Density 0.168%

    No Known Activations