© 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. 43893
    Prev
    Next
    INDEX
    Explanations

    code syntax ending with punctuation

    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
    ়
    -0.07
    缸è¾ħ缸æĪIJ
    -0.07
    ä¸įåı¯æĢĿè®®
    -0.07
    enj
    -0.06
    CAST
    -0.06
    /
    -0.06
    ////////////////////////////////////////////////////////////////////////////
    -0.06
    -0.06
    enk
    -0.05
    &
    -0.05
    POSITIVE LOGITS
    èĩªå·±
    0.12
    byname
    0.10
    èĩªå·±æ²¡æľī
    0.09
    å°Ķåħĭ
    0.08
    ertos
    0.08
    èĩªå·±èº«ä¸Ĭ
    0.08
    quo
    0.08
    δήÏĢοÏĦε
    0.08
    chia
    0.08
    tlement
    0.08
    Activations Density 0.233%

    No Known Activations