© 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. 55664
    Prev
    Next
    INDEX
    Explanations

    hope for a better future

    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
     somehow
    -0.08
    æĪĸå°ij
    -0.08
    å±ĤéĿ¢ä¸Ĭ
    -0.08
    /includes
    -0.07
    ertain
    -0.07
    ocal
    -0.07
    cad
    -0.07
     اÙĦÙĪا
    -0.07
    缸åħ³æ³ķå¾ĭ责任
    -0.07
    aps
    -0.07
    POSITIVE LOGITS
    ä½Ĩåıªè¦ģ
    0.07
    umos
    0.06
    ä¸įä»ħè¦ģ
    0.06
    ä¸įä»ħæľī
    0.06
    ä½Ĩæĺ¯å½ĵ
    0.06
     Anggota
    0.06
     reversible
    0.06
     beyond
    0.06
    ä½Ĩæĺ¯åĽłä¸º
    0.06
    åıªæľīéĢļè¿ĩ
    0.06
    Activations Density 0.253%

    No Known Activations