© 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. 27980
    Prev
    Next
    INDEX
    Explanations

    probability distributions

    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
    ä»ħä»£è¡¨ä½ľèĢħæľ¬äºº
    -0.08
    ä¸įäºī
    -0.07
    æŀĦæŀ¶
    -0.07
    ä¸įèµ°
    -0.07
    uintptr
    -0.07
    aldo
    -0.06
    ä¸Ģéģĵéģĵ
    -0.06
    åľ¨æµ·å¤ĸ
    -0.06
    éĤ¦
    -0.06
    @student
    -0.06
    POSITIVE LOGITS
     mew
    0.08
    ãĥ¢ãĥĩãĥ«
    0.08
    Named
    0.08
    оÑĤÑĢе
    0.07
    éĢĤäºİ
    0.07
     distribution
    0.07
     distributions
    0.07
     named
    0.07
    _parms
    0.07
     afl
    0.07
    Activations Density 0.013%

    No Known Activations