© 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. 15663
    Prev
    Next
    INDEX
    Explanations

    least squares and residuals

    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±¥
    -0.08
    å¤Ħäºĭ
    -0.07
    voie
    -0.07
    edar
    -0.07
    borg
    -0.07
    holm
    -0.07
     blink
    -0.07
    就读
    -0.07
    iraz
    -0.07
    ä¸įæĮ¯
    -0.06
    POSITIVE LOGITS
    lej
    0.09
    stderr
    0.08
     residuals
    0.08
    度éĩı
    0.08
    asco
    0.07
    OLD
    0.07
    èĦĬ
    0.07
     вн
    0.07
    åīįä»»
    0.07
    erial
    0.07
    Activations Density 0.002%

    No Known Activations