© 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. 63165
    Prev
    Next
    INDEX
    Explanations

    bios, language, print, Fame, analyse, summary

    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
    追究åħ¶
    -0.08
    è¶Ĭæĥ³
    -0.08
    etsk
    -0.08
    uali
    -0.08
    æľĢä¸ĵä¸ļçļĦ
    -0.08
    ä¸ĢæĿ¡é¾Ļ
    -0.08
    éĢģèµ°
    -0.07
    å°±æĢķ
    -0.07
    =$((
    -0.07
    ursed
    -0.07
    POSITIVE LOGITS
    åĴĮ交æµģ
    0.07
    aturi
    0.07
    ans
    0.06
    åħĪæĿ¥
    0.06
    æıIJ
    0.06
     puis
    0.06
    æ°Ľ
    0.06
     easy
    0.06
     floats
    0.06
    ستÙĩ
    0.06
    Activations Density 0.009%

    No Known Activations