© 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. 45825
    Prev
    Next
    INDEX
    Explanations

    avoiding fractions

    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
    loge
    -0.07
    è¶ħæłĩ
    -0.07
    hardt
    -0.07
    å¹´åįĬ
    -0.07
    ÑĥÑģка
    -0.06
     asymmetric
    -0.06
    å®ŀæĥł
    -0.06
    æľĢéķ¿
    -0.06
    _ALIGN
    -0.06
    lical
    -0.06
    POSITIVE LOGITS
    å¥½åľ¨
    0.09
    aios
    0.09
    éģ¿åħį
    0.09
     avoid
    0.08
     avoids
    0.08
     denominator
    0.08
    åºĶéģ¿åħį
    0.08
    éģ¿åħįäºĨ
    0.08
    以éģ¿åħį
    0.08
     avoiding
    0.08
    Activations Density 0.017%

    No Known Activations