© 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. 41288
    Prev
    Next
    INDEX
    Explanations

    boolean conditions or checks

    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
    zu
    -0.08
    zul
    -0.08
    صÙĦ
    -0.08
    çĶ¨æĪ·ä¸Ĭä¼ł
    -0.07
    urus
    -0.07
    isle
    -0.07
    è¨
    -0.07
    дÑĮми
    -0.07
     }>
    -0.07
    -mount
    -0.07
    POSITIVE LOGITS
    .bz
    0.07
    æľīæĿĥ
    0.06
    è¢ħè¢ħ
    0.06
    æĪĸèĢħæľī
    0.06
    以æѤ
    0.06
    istri
    0.06
    éģĩåĪ°äºĨ
    0.06
    æ¦
    0.06
    并åĪĹ
    0.06
     puss
    0.06
    Activations Density 0.014%

    No Known Activations