© 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. 29387
    Prev
    Next
    INDEX
    Explanations

    Traditionally, invention relates to

    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
    asila
    -0.08
    åĶ¯ä¸Ģ
    -0.07
    Ŀ¼
    -0.07
    axter
    -0.07
    antly
    -0.07
    åĪĩãĤĬ
    -0.07
    aina
    -0.07
    ensely
    -0.06
    åĽłåľ°
    -0.06
    anzo
    -0.06
    POSITIVE LOGITS
    è¿ijäºĽ
    0.08
    çĽ¸ä¼ł
    0.08
    ahi
    0.07
    èĥĮæĻ¯
    0.07
    âĶģâĶģâĶģâĶģâĶģâĶģâĶģâĶģ
    0.07
    grap
    0.07
    åĪļä»İ
    0.07
    æĪijä»¬çŁ¥éģĵ
    0.07
    举个ä¾ĭåŃIJ
    0.07
    orde
    0.07
    Activations Density 0.020%

    No Known Activations