© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14707
    Prev
    Next
    INDEX
    Explanations

    subset or partial

    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
    /layouts
    -0.07
    ogle
    -0.07
    央
    -0.07
    ERO
    -0.06
     Donovan
    -0.06
    ffy
    -0.06
     falla
    -0.06
    æĹłå¤Ħ
    -0.06
    æľ¬èī²
    -0.06
    meld
    -0.06
    POSITIVE LOGITS
    Subset
    0.12
     partial
    0.10
     subset
    0.10
    ä¸įå®Įæķ´
    0.10
     selective
    0.10
    Selective
    0.10
    æĪªåıĸ
    0.09
     Subset
    0.09
    imited
    0.09
     limited
    0.09
    Activations Density 0.071%

    No Known Activations