© 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. 28967
    Prev
    Next
    INDEX
    Explanations

    measurements, quantities, or rates

    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
    çĻ¾åĪĨä¹ĭçĻ¾
    -0.08
    akon
    -0.08
    ä¸ºæľŁ
    -0.07
    æĹłå¸¸
    -0.07
    ä¸Ģ对ä¸Ģ
    -0.07
    为è°ģ
    -0.07
     kız
    -0.07
    å¹´èĢģ
    -0.07
    anism
    -0.07
    aji
    -0.07
    POSITIVE LOGITS
    ilu
    0.08
    æĢ¡
    0.07
    _ALLOC
    0.07
     confortable
    0.07
    大约æĺ¯
    0.07
    ungan
    0.07
     rarely
    0.07
     comfortable
    0.07
     uttered
    0.07
    ä¼°ç®Ĺ
    0.07
    Activations Density 0.010%

    No Known Activations