© 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. 22445
    Prev
    Next
    INDEX
    Explanations

    command, option, or status

    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°½åı¯èĥ½åľ°
    -0.07
    )?.
    -0.07
    çļĦè¿Ļç§į
    -0.07
    ,$
    -0.06
    x
    -0.06
    és
    -0.06
    -
    -0.06
     ↵↵↵
    -0.06
    ä¸įä»ħèĥ½å¤Ł
    -0.06
     Furthermore
    -0.06
    POSITIVE LOGITS
    _BREAK
    0.08
    odesk
    0.08
    onnal
    0.08
      ↵
    0.08
    rave
    0.07
     ìĹĨìĿĮ
    0.07
     gär
    0.07
    <br
    0.07
    letcher
    0.07
    ;break
    0.07
    Activations Density 0.009%

    No Known Activations