© 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. 4324
    Prev
    Next
    INDEX
    Explanations

    sign in, your usual

    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
    inbox
    -0.08
    aval
    -0.07
    cxx
    -0.07
    æºIJåľ°
    -0.07
    éħĿ
    -0.07
    INET
    -0.07
     blinking
    -0.07
    ĽĦ
    -0.06
    ptions
    -0.06
    visor
    -0.06
    POSITIVE LOGITS
    ãĥĥãĤº
    0.07
    exerc
    0.06
    öv
    0.06
    æľ¬
    0.06
    enn
    0.06
    Y
    0.06
     Regents
    0.06
     tokenId
    0.06
    æĹłè®ºæĺ¯åľ¨
    0.06
    æ°¸ä¹IJ
    0.06
    Activations Density 0.002%

    No Known Activations