© 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. 49039
    Prev
    Next
    INDEX
    Explanations

    function, cost, energy, loss

    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
    榴
    -0.08
    å¼Ĥ
    -0.06
    å¾Ĵæīĭ
    -0.06
    æķ¬è¯·åħ³æ³¨
    -0.06
    engar
    -0.06
    dings
    -0.06
    çķ°
    -0.06
    ow
    -0.06
     ex
    -0.06
    財
    -0.06
    POSITIVE LOGITS
    åı¦ä¸ĢåįĬ
    0.08
    .exports
    0.08
     phạt
    0.07
    ä½ĵéĩı
    0.07
    .functional
    0.07
    管çIJĨç³»ç»Ł
    0.07
    åı¯è§Ĥ
    0.07
    大秦
    0.07
    æĥ©ç½ļ
    0.07
     uÄŁ
    0.07
    Activations Density 0.001%

    No Known Activations