© 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. 16691
    Prev
    Next
    INDEX
    Explanations

    negative scores or differential

    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
    itze
    -0.07
    awat
    -0.07
    iski
    -0.06
    太åı¤
    -0.06
    pere
    -0.06
    ipro
    -0.06
    ä¿¡ãģĺ
    -0.06
    é¥
    -0.06
    æľīæĿ¡ä¸įç´Ĭ
    -0.06
    å®Ŀ座
    -0.06
    POSITIVE LOGITS
     negative
    0.08
    onus
    0.08
    .ZERO
    0.08
    áĢĽáĢ¾
    0.08
    æ¸ħ鼶
    0.08
    å®ļä¹ī为
    0.08
    Negative
    0.08
    negative
    0.08
    éķ¿çŁŃ
    0.08
    ä¸įå¹³
    0.08
    Activations Density 0.020%

    No Known Activations