© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17752
    Prev
    Next
    INDEX
    Explanations

    clarifies, fits in, proclaims, excited to, raises, highlights, unable to, demonstrates, results

    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
    reon
    -0.08
    yme
    -0.08
    çİĦæѦ
    -0.07
    iant
    -0.07
    æķ´ä½ĵä¸Ĭ
    -0.07
    ppure
    -0.07
    _ENTRY
    -0.07
    ĥģ
    -0.07
    uttore
    -0.07
     pageable
    -0.07
    POSITIVE LOGITS
    acu
    0.07
    acan
    0.07
    ä¸įäºĨ
    0.07
    pä
    0.07
    lah
    0.06
    eah
    0.06
    ifu
    0.06
    blas
    0.06
    stw
    0.06
    äºĨ对
    0.06
    Activations Density 0.557%

    No Known Activations