© 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. 31192
    Prev
    Next
    INDEX
    Explanations

    then it

    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
    å¿ħé¡»çĶ±
    -0.07
    æĽ´é«ĺçļĦè¦ģæ±Ĥ
    -0.07
    _Build
    -0.07
    ä¸įæĸŃæݢ索
    -0.07
    ään
    -0.07
    æīĢ以å½ĵ
    -0.07
    建ç«ĭåľ¨
    -0.06
    åıįæĢĿ
    -0.06
     donc
    -0.06
    strup
    -0.06
    POSITIVE LOGITS
     resulting
    0.08
    çħ§æł·
    0.08
     surprisingly
    0.08
    ï´
    0.08
    ä»įèĥ½
    0.08
    ç«Ł
    0.07
     subsequently
    0.07
    elok
    0.07
     afterward
    0.07
    许åı¯
    0.07
    Activations Density 0.378%

    No Known Activations