© 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. 47734
    Prev
    Next
    INDEX
    Explanations

    numbers and units of measure

    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
    æĪIJåįĥ
    -0.07
    çļĦ大åŀĭ
    -0.07
    ena
    -0.07
    åºŀ大
    -0.07
    ieno
    -0.07
    çĻ¾äº¿
    -0.07
    vast
    -0.06
    =no
    -0.06
    és
    -0.06
    gre
    -0.06
    POSITIVE LOGITS
     Pearce
    0.08
    年以ä¸Ĭ
    0.08
    еÑĤÑĢо
    0.08
     tiro
    0.08
    komm
    0.08
    äºĶæĺŁ
    0.07
    PEAR
    0.07
    erox
    0.07
    çľĭçľĭåIJ§
    0.07
     Legislat
    0.07
    Activations Density 0.526%

    No Known Activations