© 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. 24648
    Prev
    Next
    INDEX
    Explanations

    may not know

    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
    à¹ģà¸ĭ
    -0.07
    FromArray
    -0.07
     olsa
    -0.07
    itmap
    -0.07
    éro
    -0.07
     Laz
    -0.07
    oine
    -0.07
    IMPLEMENT
    -0.07
    çļĦç¡®æĺ¯
    -0.07
    客æĪ·è¦ģæ±Ĥ
    -0.07
    POSITIVE LOGITS
    igt
    0.07
    åĴļåĴļ
    0.07
    åı¦å¤ĸ
    0.07
    åıĪæĪĸèĢħ
    0.07
    ÃĵG
    0.07
    å°¤åħ¶
    0.07
    IGA
    0.07
    elah
    0.06
    çŁ¥
    0.06
    ä¹Łåı¯èĥ½
    0.06
    Activations Density 0.017%

    No Known Activations