© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 10957
    Prev
    Next
    INDEX
    Explanations

    stopping actions and negative events

    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
    çľŁå¥½
    -0.08
    bor
    -0.08
    åĪĨ身
    -0.07
    iggins
    -0.07
    ãĤ³ãĥĦ
    -0.07
    teen
    -0.07
    _uniform
    -0.07
     ì±Ļ
    -0.07
    å°ijå¹´åĦ¿ç«¥
    -0.07
    eens
    -0.07
    POSITIVE LOGITS
     temporarily
    0.09
    æļĤæŶ
    0.09
    继ç»Ń
    0.08
    æ¶īäºĭ
    0.08
     altogether
    0.08
     offending
    0.08
    æŀľæĸŃ
    0.08
    æļĤåģľ
    0.08
    åıĹå½±åĵį
    0.08
    æļĤç¼ĵ
    0.08
    Activations Density 0.188%

    No Known Activations