© 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. 18469
    Prev
    Next
    INDEX
    Explanations

    time zones DST

    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
    воло
    -0.08
     Cama
    -0.08
    IRTUAL
    -0.08
    placer
    -0.08
    опеÑĢа
    -0.08
    ãģłãģijãģ§ãģªãģı
    -0.07
    ÃģC
    -0.07
    lyph
    -0.07
     ë¿IJë§Į
    -0.07
    cina
    -0.07
    POSITIVE LOGITS
    çŃīåħ¶ä»ĸ
    0.11
    çŃīåĽłç´ł
    0.09
    æĪĸåħ¶ä»ĸ
    0.08
    çļĦåŃĺåľ¨
    0.08
    åĽłç´łçļĦå½±åĵį
    0.08
    çŃīæĥħåĨµ
    0.08
    çŃīåİŁåĽł
    0.08
    åĽłç´łå½±åĵį
    0.08
    çļĦå½±åĵį
    0.08
    æĪĸåħ¶å®ĥ
    0.08
    Activations Density 0.028%

    No Known Activations