© 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. 21664
    Prev
    Next
    INDEX
    Explanations

    extrapolated, modeled, waveform, brightness

    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
    nection
    -0.08
    á»ĵn
    -0.07
    ¬ģ
    -0.07
    ruc
    -0.06
     mut
    -0.06
    çĴ
    -0.06
    èĤīçľ¼
    -0.06
    çĭ¬ç«ĭæĢĿèĢĥ
    -0.06
     tackles
    -0.06
    LayoutPanel
    -0.06
    POSITIVE LOGITS
    ParameterValue
    0.08
    éŨåīį
    0.08
    æľ«
    0.07
     ramp
    0.07
    鸡汤
    0.07
    inz
    0.07
    -overlay
    0.07
    亨
    0.07
    propri
    0.07
    è¿ĩ头
    0.07
    Activations Density 0.033%

    No Known Activations