© 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. 9300
    Prev
    Next
    INDEX
    Explanations

    over generalization, definitive statement, drastic action

    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
    elseif
    -0.08
     tâ
    -0.08
    LOSE
    -0.08
    ëŀij
    -0.08
    Ø´ØŃ
    -0.07
    å®ŀè´¨
    -0.07
    æºIJæºIJ
    -0.07
    ignum
    -0.07
     '::
    -0.07
    ulich
    -0.07
    POSITIVE LOGITS
     absol
    0.08
     assertions
    0.08
     claims
    0.07
    è¯Ŀ说
    0.07
     blanket
    0.07
     statements
    0.07
     pron
    0.07
    éĢļåĪĻ
    0.06
    对ç«ĭ
    0.06
    ä¸įåı¯èĥ½çļĦ
    0.06
    Activations Density 0.008%

    No Known Activations