© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 61772
    Prev
    Next
    INDEX
    Explanations

    chemical groups and suffixes

    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
    <|box_end|>
    -0.11
    ÄIJT
    -0.08
    æľīæīĢä¸ĭéĻį
    -0.08
    ðŁĺī
    -0.08
    æĤīå¿ĥ
    -0.08
     Isk
    -0.08
    isia
    -0.08
    olari
    -0.08
    ä¸įçŁ¥æīĢ
    -0.08
    /lists
    -0.08
    POSITIVE LOGITS
     (
    0.08
    åıĪ称
    0.08
    ä¹Łå°±æĺ¯
    0.07
     cioè
    0.07
    0.07
    åıĪåIJį
    0.06
    ä¹ĭæģĭ
    0.06
    æĪĸèĢħ说
    0.06
    åį³
    0.06
    -
    0.06
    Activations Density 0.018%

    No Known Activations