© 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. 10294
    Prev
    Next
    INDEX
    Explanations

    fraction computations

    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
    è°¬
    -0.06
    ROWS
    -0.06
    è°
    -0.06
    绣
    -0.06
    c
    -0.06
    orm
    -0.06
    ofil
    -0.06
     eb
    -0.06
    b
    -0.06
     Gul
    -0.06
    POSITIVE LOGITS
     ratios
    0.10
     ratio
    0.10
    æ¯Ķä¾ĭ为
    0.10
     Ratio
    0.09
    ratio
    0.09
     ë¹Ħìľ¨
    0.09
    _ratio
    0.09
    ÙĨز
    0.08
    izzera
    0.08
    æ¯Ķçİĩ
    0.08
    Activations Density 0.005%

    No Known Activations