© 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. 21032
    Prev
    Next
    INDEX
    Explanations

    number 2 in equations

    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
     Downs
    -0.09
    (es
    -0.09
    abis
    -0.08
    enhagen
    -0.08
    âĪĢ
    -0.08
    tdown
    -0.08
    dex
    -0.08
    mung
    -0.08
    pedo
    -0.08
    orme
    -0.08
    POSITIVE LOGITS
     NR
    0.07
    eline
    0.06
     rad
    0.06
     mand
    0.06
    ä¸įåIJ¬
    0.06
    åĢ¡å¯¼
    0.06
     co
    0.05
    mand
    0.05
     radial
    0.05
    åįĹè¡Ĺ
    0.05
    Activations Density 0.003%

    No Known Activations