© 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. 33979
    Prev
    Next
    INDEX
    Explanations

    numbers and units (m, mg, C, km, GB)

    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
    çī¹æ®Ĭ
    -0.07
    æĶ¾çĿĢ
    -0.07
    avig
    -0.06
     special
    -0.06
    éĻ¤
    -0.06
    åĪ©çĶ¨
    -0.06
    çŁ¥éģĵæĪij
    -0.06
    irect
    -0.06
    æIJ¬åĪ°
    -0.06
    ç®
    -0.06
    POSITIVE LOGITS
    ijľ
    0.10
     voire
    0.09
    è¿Ļ个æķ°åŃĹ
    0.09
    orso
    0.08
    å¿ĹåĪļ
    0.08
    æĪĸ以ä¸Ĭ
    0.08
    _tokenize
    0.08
    <quote
    0.07
    åĪļåĪļ好
    0.07
    .setdefault
    0.07
    Activations Density 0.003%

    No Known Activations