© 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. 41435
    Prev
    Next
    INDEX
    Explanations

    mathematical partitioning

    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
    èĭ«
    -0.07
    æľīåIJį
    -0.07
    oload
    -0.07
    论æĸĩçļĦ
    -0.06
     Lomb
    -0.06
     obro
    -0.06
     LM
    -0.06
    éĶµ
    -0.06
    éĴŁå£°
    -0.06
    hung
    -0.06
    POSITIVE LOGITS
    wür
    0.07
    nesia
    0.07
     Ø®ÙĦÙĬÙĦ
    0.07
     colore
    0.07
    å¿ħ究
    0.07
    _Color
    0.07
    ëį°ìĿ´
    0.07
     scom
    0.07
    说ä¸į
    0.07
    èī²åĪĹ
    0.07
    Activations Density 0.004%

    No Known Activations