© 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. 58239
    Prev
    Next
    INDEX
    Explanations

    vs. or differing

    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
    ominated
    -0.07
    åľ¨åľ°
    -0.07
    _pb
    -0.07
    antha
    -0.07
    leh
    -0.07
    ular
    -0.07
    á»ĥn
    -0.06
    ufa
    -0.06
    arent
    -0.06
    UF
    -0.06
    POSITIVE LOGITS
     versus
    0.22
     vs
    0.21
    ä¸įåIJĮçļĦ
    0.17
    _vs
    0.17
    vs
    0.16
    çļĦä¸įåIJĮ
    0.16
    -vs
    0.15
     different
    0.15
     Different
    0.15
     differing
    0.15
    Activations Density 0.304%

    No Known Activations