© 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. 19809
    Prev
    Next
    INDEX
    Explanations

    perforated fences, porous structure, honeycomb

    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
    å°ī
    -0.08
    ä¸Ģåīij
    -0.08
    温度çļĦ
    -0.07
    eka
    -0.07
     duration
    -0.07
    دÙħ
    -0.07
    èµ
    -0.06
     Wrapper
    -0.06
     overweight
    -0.06
     rewritten
    -0.06
    POSITIVE LOGITS
    å¯ĨéĽĨçļĦ
    0.16
    å¯ĨéĽĨ
    0.16
    å¯Ĩå¯Ĩ麻麻
    0.14
    ç¨Ģçĸı
    0.14
    å¯Ĩå¸ĥ
    0.13
    æİĴåĪĹ
    0.13
    sparse
    0.11
    dense
    0.11
    éĹ´è·Ŀ
    0.11
     dense
    0.11
    Activations Density 0.363%

    No Known Activations