© 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. 65019
    Prev
    Next
    INDEX
    Explanations

    equations with single letter variables

    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
     Olah
    -0.07
    esch
    -0.07
    aber
    -0.07
    egos
    -0.07
    éĺĻ
    -0.07
    å°±æĺ¯è¿Ļ个
    -0.06
    éĩijå®Ŀ
    -0.06
    .gg
    -0.06
    cast
    -0.06
    _NATIVE
    -0.06
    POSITIVE LOGITS
    移åĪ°
    0.07
    apos
    0.07
    omen
    0.07
    è¿IJ
    0.07
    леÑģ
    0.07
    æĶ¶æĭ¾
    0.07
    arz
    0.06
    _PT
    0.06
    ohen
    0.06
     Rear
    0.06
    Activations Density 0.028%

    No Known Activations