© 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. 58003
    Prev
    Next
    INDEX
    Explanations

    search tree

    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
    大ä¸ĸçķĮ
    -0.10
    cket
    -0.09
    ocs
    -0.08
    æľ¬å°ı说
    -0.08
    ç¯ĩå°ı说
    -0.08
    åħĭ森
    -0.08
    ubern
    -0.08
    iams
    -0.08
    esan
    -0.08
    اپ
    -0.08
    POSITIVE LOGITS
    汶
    0.07
     val
    0.06
     Val
    0.06
    ç³»çļĦ
    0.06
    å½±
    0.06
    å²IJ
    0.06
    ARIANT
    0.06
    çĿģå¼Ģ
    0.06
    è·¯çĶ±
    0.06
    oli
    0.06
    Activations Density 0.215%

    No Known Activations