© 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. 41743
    Prev
    Next
    INDEX
    Explanations

    closing tokens for code or math

    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
     tròn
    -0.07
    noi
    -0.07
     Suy
    -0.07
    æĹ¥åĨħ
    -0.07
    _Reference
    -0.07
    åĩºçīĪçļĦ
    -0.07
    enaar
    -0.07
    èĥ¤
    -0.07
    éĩijæ¦ľ
    -0.07
    ä¸İç»´ä¿®
    -0.07
    POSITIVE LOGITS
    çī¹å°Ķ
    0.08
    <|box_end|>
    0.08
    semble
    0.07
    ambu
    0.07
    çĿ¦
    0.07
    ä¸įçŁ¥éģĵæĢİä¹Ī
    0.07
    áĥ§
    0.07
    JAKARTA
    0.07
    oskop
    0.07
    åĬłæĭ¿å¤§
    0.07
    Activations Density 0.004%

    No Known Activations