© 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. 34276
    Prev
    Next
    INDEX
    Explanations

    formulas and exponents

    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
    循
    -0.08
    asm
    -0.07
    Seriously
    -0.07
    çŃīåħ¶ä»ĸ
    -0.07
    ä»»ä½ķåħ¶ä»ĸ
    -0.07
    вл
    -0.07
     altre
    -0.07
    ä¸įéĻIJ
    -0.07
    è¾ĥ
    -0.07
    åĪºæ¿Ģ
    -0.07
    POSITIVE LOGITS
     exponential
    0.09
     formulas
    0.09
    类似
    0.08
    arih
    0.08
    类似äºİ
    0.08
     coefficients
    0.08
    formula
    0.08
    åħ¬å¼ı
    0.08
     logarith
    0.08
    éłŃãģ«
    0.08
    Activations Density 0.042%

    No Known Activations