© 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. 13855
    Prev
    Next
    INDEX
    Explanations

    č

    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
    çŀij
    -0.08
    çĬ¶æĢģä¸ĭ
    -0.08
    çĮĽè¿Ľ
    -0.08
    Fcn
    -0.07
    森çļĦ
    -0.07
    åIJĦ项任åĬ¡
    -0.07
    iele
    -0.07
    æĺ¯ä¸Ģ缴
    -0.07
    @foreach
    -0.07
     Reit
    -0.07
    POSITIVE LOGITS
     if
    0.08
    åŃ
    0.06
    	if
    0.06
    åĽł
    0.06
    if
    0.06
    utch
    0.06
     Richards
    0.06
    ÏĥÏĦη
    0.06
     except
    0.06
    é£Ł
    0.06
    Activations Density 0.037%

    No Known Activations