© 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. 16016
    Prev
    Next
    INDEX
    Explanations

    symbols following mathematical terms

    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
    åĬłæĭ¿å¤§
    -0.07
    ingar
    -0.06
    ়
    -0.06
    æģķ
    -0.06
    åĭĩå¾Ģ缴åīį
    -0.06
    i
    -0.06
    æĸ°åĬłåĿ¡
    -0.06
    is
    -0.06
    ppure
    -0.06
     neither
    -0.06
    POSITIVE LOGITS
    urator
    0.09
    olvable
    0.08
    agnol
    0.08
    åijIJ
    0.08
    menta
    0.08
    olio
    0.08
    ymm
    0.08
    sev
    0.08
    oghi
    0.08
    ungk
    0.08
    Activations Density 0.011%

    No Known Activations