© 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. 29126
    Prev
    Next
    INDEX
    Explanations

    test, fix, should, is, for

    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
    ’
    -0.07
    ‘
    -0.06
    ,
    -0.06
    *
    -0.06
    ?
    -0.06
    as
    -0.06
     (
    -0.06
     —
    -0.06
    anda
    -0.06
     ,
    -0.06
    POSITIVE LOGITS
     rowspan
    0.09
    æľĢæĸ°æĸĩç«ł
    0.09
    .SM
    0.09
    èº
    0.09
    ."&
    0.08
    ¬
    0.08
    iog
    0.08
    æľĢæĸ°è¯Ħ论
    0.08
    erset
    0.08
    ç©«
    0.08
    Activations Density 0.008%

    No Known Activations