© 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. 15518
    Prev
    Next
    INDEX
    Explanations

    table headings or labels

    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
    .FC
    -0.07
    çĤ¹å¤ļ
    -0.07
    èĩĬ
    -0.07
    容æĺĵéĢłæĪIJ
    -0.07
    /+
    -0.07
    uble
    -0.07
    åĭĺ
    -0.07
    _HINT
    -0.07
    -law
    -0.07
    Ïĥιά
    -0.07
    POSITIVE LOGITS
    wend
    0.08
    åĪ¥
    0.08
    à¤Ĺत
    0.07
    ë³Ħ
    0.07
    cope
    0.07
    åIJį称
    0.07
    ifer
    0.07
    anam
    0.07
     Lud
    0.07
    дам
    0.07
    Activations Density 0.067%

    No Known Activations