© 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. 16153
    Prev
    Next
    INDEX
    Explanations

    nothing changes

    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
    eph
    -0.08
    æĽ´å®¹æĺĵ
    -0.07
    æģ¨ä¸įå¾Ĺ
    -0.07
    kowo
    -0.07
    icut
    -0.07
    æ¯Ķè¾ĥ容æĺĵ
    -0.07
    freund
    -0.07
    çĵ¦è§£
    -0.07
     easily
    -0.07
    ä¹Łå®¹æĺĵ
    -0.07
    POSITIVE LOGITS
     unchanged
    0.16
    ä¸įåıĺ
    0.12
    ä¿ĿæĮģä¸įåıĺ
    0.11
     unaffected
    0.11
    ä¸įåıĺçļĦ
    0.11
    ä¸įè®Ĭ
    0.10
    æĹ¢ä¸į
    0.10
    ä¸įåıijçĶŁ
    0.10
    unch
    0.10
     preserves
    0.10
    Activations Density 0.045%

    No Known Activations