© 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. 40011
    Prev
    Next
    INDEX
    Explanations

    floating point operations

    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
     statistically
    -0.07
    桦
    -0.07
    hed
    -0.07
     intricate
    -0.07
    λε
    -0.06
    èĩªéĢĤåºĶ
    -0.06
    ẳng
    -0.06
    ély
    -0.06
     Geh
    -0.06
     sequ
    -0.06
    POSITIVE LOGITS
    ukka
    0.08
     Sutton
    0.08
    å¿«æį·
    0.08
    umper
    0.08
    okies
    0.08
    _every
    0.07
    红æ¢ħ
    0.07
    eton
    0.07
    otti
    0.07
    imd
    0.07
    Activations Density 0.004%

    No Known Activations