© 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. 28234
    Prev
    Next
    INDEX
    Explanations

    +/- symbols or values

    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
    ÏĦζ
    -0.09
    ãĥ¼ãĤ¸ãĥ¼
    -0.07
     khiêm
    -0.07
    ä»İèĢĮæıIJé«ĺ
    -0.07
    flen
    -0.07
    ervis
    -0.07
    alap
    -0.07
    è°¦
    -0.07
    horn
    -0.07
    bpp
    -0.07
    POSITIVE LOGITS
    漪
    0.07
    enom
    0.06
    çļĨåı¯
    0.06
    åħ¶ä¸Ńä¹ĭä¸Ģ
    0.06
    zet
    0.06
    .opend
    0.06
    matching
    0.06
    Matching
    0.06
    çļĦéĢīæĭ©
    0.06
    çĪ½å¿«
    0.06
    Activations Density 0.001%

    No Known Activations