© 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. 9877
    Prev
    Next
    INDEX
    Explanations

    strength training and performance

    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
    éĩİé¤IJ
    -0.07
     Miles
    -0.07
     km
    -0.07
    åĨĹ
    -0.06
     embedding
    -0.06
    é¥®é£Łä¹łæĥ¯
    -0.06
     slit
    -0.06
    icket
    -0.06
    statuses
    -0.06
    ÅĤos
    -0.06
    POSITIVE LOGITS
    åĻ¨æ¢°
    0.10
     repetitions
    0.09
     Ñģи
    0.09
     Strength
    0.09
    èĩªéĩį
    0.09
     strength
    0.09
    åĮ®
    0.09
    è®Ńç»ĥä¸Ń
    0.09
    strength
    0.09
     reps
    0.09
    Activations Density 0.068%

    No Known Activations