© 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. 46929
    Prev
    Next
    INDEX
    Explanations

    cooperation with

    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
    eens
    -0.08
    å¾·æĭī
    -0.08
    ecast
    -0.07
    สà¹Į
    -0.07
    nis
    -0.07
    åĢ¼çļĦ
    -0.07
    곤
    -0.06
    à¸Ĥà¸Ńà¸ĩà¸Ħวาม
    -0.06
    raj
    -0.06
    ured
    -0.06
    POSITIVE LOGITS
    æĹłéĹ´
    0.11
    夥伴
    0.10
    åħ±èµ¢
    0.09
    hangi
    0.09
    ниÑĨÑĮ
    0.08
    RootElement
    0.08
    é»ĺå¥ij
    0.08
    hips
    0.08
    idge
    0.08
    度é«ĺ
    0.08
    Activations Density 0.054%

    No Known Activations