© 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. 29303
    Prev
    Next
    INDEX
    Explanations

    copyrights and licenses

    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
    udd
    -0.08
    å±ħé«ĺ
    -0.08
    outers
    -0.08
    æľ¬ç½ij
    -0.07
    lit
    -0.07
    浩
    -0.07
    è°¦
    -0.07
    é¦Ĩéķ¿
    -0.07
    -archive
    -0.07
    cp
    -0.07
    POSITIVE LOGITS
    åįĥéĩĮ
    0.07
    å¸ĥéĩĮ
    0.07
     setObject
    0.07
     Asi
    0.06
    gol
    0.06
    verity
    0.06
    æĢªä¸įå¾Ĺ
    0.06
    å¿«çļĦ
    0.06
    åħ¶å®ĥçļĦ
    0.06
    å¸ĥçļĦ
    0.06
    Activations Density 0.006%

    No Known Activations