© 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. 11564
    Prev
    Next
    INDEX
    Explanations

    random and fractional values

    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
    rame
    -0.08
    åªĴ
    -0.07
     handjob
    -0.07
    æĭĦ
    -0.07
    ahasan
    -0.07
    ä¼IJ
    -0.07
    rary
    -0.07
    è¿ľæĻ¯
    -0.07
    èģĺ
    -0.07
    ieso
    -0.07
    POSITIVE LOGITS
     fractional
    0.09
    åħ¥çĿ¡
    0.08
     Fraction
    0.08
    å°ıæķ°
    0.07
    .overflow
    0.07
    มูล
    0.07
    çĿ¡ä¸įçĿĢ
    0.07
    fraction
    0.07
    ç¸
    0.07
     fraction
    0.07
    Activations Density 0.006%

    No Known Activations