© 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. 20858
    Prev
    Next
    INDEX
    Explanations

    repeating units or polymer chains

    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
     staged
    -0.07
     Weinstein
    -0.07
     overd
    -0.07
     Artis
    -0.07
    ÏĩÏį
    -0.07
    è§Ħ模çļĦ
    -0.07
    umfang
    -0.07
    åĺ´
    -0.07
    èĢĮæѤæŶ
    -0.07
     жал
    -0.07
    POSITIVE LOGITS
    äº¤æĽ¿
    0.13
     alternating
    0.12
    ÑĩеÑĢед
    0.10
     altern
    0.09
    交éĶĻ
    0.09
    éĵ¾
    0.08
    åĸ®åħĥ
    0.08
    æ¯ıéļĶ
    0.08
    èĢIJå¯Ĵ
    0.08
     periodically
    0.08
    Activations Density 0.025%

    No Known Activations