© 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. 9332
    Prev
    Next
    INDEX
    Explanations

    threshold / value / dividing / crossover / point

    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
     repeat
    -0.08
    _SLOT
    -0.08
    -repeat
    -0.08
    ç½ijç«Ļ导èĪª
    -0.08
    æİĸ
    -0.07
    ì±Ħ
    -0.07
    ajer
    -0.07
    esn
    -0.07
    æĪĸéĥ¨åĪĨ
    -0.07
    Repeat
    -0.07
    POSITIVE LOGITS
     separating
    0.11
     switch
    0.11
    çķĮ线
    0.10
    çķĮéĻIJ
    0.10
    éĺĪåĢ¼
    0.10
    åĪĨæ°´
    0.10
     crossover
    0.10
     switches
    0.10
     threshold
    0.10
    .switch
    0.10
    Activations Density 0.077%

    No Known Activations