© 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. 9692
    Prev
    Next
    INDEX
    Explanations

    heterocyclic compounds

    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´¾
    -0.07
    åīĥ
    -0.07
    haj
    -0.07
    åIJĦç§ij
    -0.07
    asal
    -0.07
    èIJ½èĬ±
    -0.07
    çŀ©
    -0.07
    <|box_end|>
    -0.07
    inach
    -0.06
    nee
    -0.06
    POSITIVE LOGITS
    ugar
    0.08
    çijŀæĭī
    0.08
    è°·
    0.07
    organic
    0.07
    MouseButton
    0.07
    unic
    0.07
     thoát
    0.06
    éĿŀéĩijå±ŀ
    0.06
    BYTE
    0.06
    èĻļå¿ĥ
    0.06
    Activations Density 0.023%

    No Known Activations