© 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. 40034
    Prev
    Next
    INDEX
    Explanations

    numbers followed by punctuation or words

    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
    è¡Įä¹ĭ
    -0.06
     mirac
    -0.06
    ç´§ç´§åĽ´ç»ķ
    -0.06
    iams
    -0.06
     ØŃدÙĪد
    -0.06
    ç¥ŀä»Ļ
    -0.06
    åĨįæľī
    -0.06
     near
    -0.06
     prem
    -0.06
    å¢ĥ
    -0.06
    POSITIVE LOGITS
    emachine
    0.08
    åłĤ
    0.08
    enaire
    0.08
    bsite
    0.08
    getExtension
    0.08
    ventura
    0.07
    elv
    0.07
    entic
    0.07
    written
    0.07
    OfSize
    0.07
    Activations Density 0.004%

    No Known Activations