© 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. 25414
    Prev
    Next
    INDEX
    Explanations

    time, hex, wavelength, relative, calories

    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
    eron
    -0.08
    æ©
    -0.07
    hir
    -0.07
    avis
    -0.07
    avel
    -0.07
     iepazÄ«Å¡anÄģs
    -0.07
    çļĦæ¸ħ
    -0.07
    ä¹Łä¸įä¾ĭå¤ĸ
    -0.06
    croft
    -0.06
    头çļĦ
    -0.06
    POSITIVE LOGITS
    itution
    0.08
    emap
    0.07
    åIJĬ
    0.07
    onse
    0.07
    rose
    0.07
    èijĨ
    0.07
    EME
    0.07
     Infer
    0.06
    éİĸ
    0.06
     inferred
    0.06
    Activations Density 0.123%

    No Known Activations