© 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. 29907
    Prev
    Next
    INDEX
    Explanations

    winding and wrapping materials

    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
    è¯Ľ
    -0.07
     blasts
    -0.07
    inia
    -0.07
     chast
    -0.07
     timid
    -0.06
     structures
    -0.06
    iels
    -0.06
    ç»´
    -0.06
     potent
    -0.06
    éĢļéĢı
    -0.06
    POSITIVE LOGITS
    ç¼łç»ķ
    0.10
     rapi
    0.09
    ä¸Ģ端
    0.09
    -loop
    0.09
     loop
    0.08
    ä¸Ģåį·
    0.08
     tension
    0.08
     loops
    0.08
    Loop
    0.08
    çIJĨ顺
    0.08
    Activations Density 0.059%

    No Known Activations