© 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. 38412
    Prev
    Next
    INDEX
    Explanations

    compare, depend, have, started, generic, character, showing

    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
    blend
    -0.08
    ivec
    -0.08
    FETCH
    -0.08
    ÐĵС
    -0.07
    normalize
    -0.07
    éĢĤ度çļĦ
    -0.07
    åºĶå¾ģ
    -0.07
    rouch
    -0.07
    ilha
    -0.07
    areth
    -0.07
    POSITIVE LOGITS
    å²Ĥä¸įæĺ¯
    0.13
     would
    0.09
     somehow
    0.09
     müsste
    0.09
     unnecessarily
    0.09
    åıĪè¦ģ
    0.08
     Would
    0.08
     müssten
    0.08
    ä¹Łå¤ª
    0.08
     ÑıкобÑĭ
    0.08
    Activations Density 0.110%

    No Known Activations