© 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. 34049
    Prev
    Next
    INDEX
    Explanations

    command line tools

    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
    (/^\
    -0.08
    ä¹ĭåIJİå°±
    -0.08
    edList
    -0.08
    ingly
    -0.08
    edly
    -0.08
    ussen
    -0.07
    ä¸ĢåłĤ
    -0.07
    èĪ¬åľ°
    -0.07
    åħŃä¸ĥ
    -0.07
    asionally
    -0.07
    POSITIVE LOGITS
    缮çļĦ
    0.07
    ij
    0.07
    uda
    0.06
    æĪĸå¤ļ个
    0.06
    æĥ³çŁ¥éģĵ
    0.06
     tender
    0.06
    iso
    0.06
    iri
    0.06
    èĬ±
    0.06
    ugen
    0.06
    Activations Density 0.085%

    No Known Activations