© 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. 10819
    Prev
    Next
    INDEX
    Explanations

    dates and code 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
    enten
    -0.07
    миÑĢа
    -0.07
    å¤ĸéĵ¾
    -0.07
    ég
    -0.07
    è·»
    -0.07
    skog
    -0.07
    unik
    -0.07
    ent
    -0.07
    ä¸İæĸĩåĮĸ
    -0.07
     ìĬ¬
    -0.07
    POSITIVE LOGITS
    çī¢
    0.07
    à§ĭল
    0.06
    éĶ¦ç»£
    0.06
    ì½ĺ
    0.06
    oms
    0.06
    raul
    0.06
    æķ´å¥Ĺ
    0.06
    erts
    0.06
    åħ¨ç½ij
    0.06
    adar
    0.06
    Activations Density 0.001%

    No Known Activations