© 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. 49030
    Prev
    Next
    INDEX
    Explanations

    code punctuation and data separators

    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
    ach
    -0.08
    onta
    -0.07
    nonnull
    -0.07
    cich
    -0.06
    _stride
    -0.06
    çļĦè¿ij
    -0.06
    rosso
    -0.06
    prototype
    -0.06
    çĹħåѦ
    -0.06
    uke
    -0.06
    POSITIVE LOGITS
    ufe
    0.08
    fos
    0.07
    å²ģéĤ£å¹´
    0.07
    æĪijèĩª
    0.07
    ä½łåģļ
    0.07
    好èĩªå·±çļĦ
    0.07
    ä»°
    0.07
    åĸ®ç´Ķ
    0.07
    è¦ģé«ĺ
    0.06
    ÙĬÙĩ
    0.06
    Activations Density 0.003%

    No Known Activations