© 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. 20228
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas and symbols

    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
    åħ¢åħ¢
    -0.08
    —
    -0.06
    —a
    -0.06
    rach
    -0.06
     calab
    -0.06
    ç±½
    -0.06
    _ENDIAN
    -0.06
     P
    -0.05
    çµ
    -0.05
    ä½Ĩèĩ³å°ij
    -0.05
    POSITIVE LOGITS
    对人类
    0.09
    yser
    0.09
    å¡ļ
    0.08
     dikutip
    0.08
    prost
    0.08
    oltip
    0.08
    гоÑĢа
    0.08
    对人çļĦ
    0.08
    kers
    0.08
    Ø°ÙĦ
    0.07
    Activations Density 0.018%

    No Known Activations