© 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. 49882
    Prev
    Next
    INDEX
    Explanations

    H, C, Polo, Java, log

    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
    _SEL
    -0.07
    ÑĨ
    -0.06
     âĿ
    -0.06
    romise
    -0.06
    vn
    -0.06
    æľĢéĩįè¦ģçļĦæĺ¯
    -0.06
    ä¾į
    -0.06
    ½ij
    -0.06
    arque
    -0.06
    oto
    -0.06
    POSITIVE LOGITS
    orton
    0.09
    ber
    0.08
    berge
    0.08
    å¢Ł
    0.08
    azzi
    0.08
     Beb
    0.08
    伯çī¹
    0.07
     appunto
    0.07
    brick
    0.07
     anyways
    0.07
    Activations Density 0.032%

    No Known Activations