© 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. 23986
    Prev
    Next
    INDEX
    Explanations

    conjunctions and verbs

    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
    å°±ä¸Ģå®ļ
    -0.08
     degusta
    -0.08
    ãģ£ãģ¡ãĤĥãģĨ
    -0.08
     ÑĥвеÑĢенÑĭ
    -0.08
    çļĦè¿ĺæľī
    -0.08
     weren
    -0.07
     semb
    -0.07
     asisti
    -0.07
    æķ°æį®çºłéĶĻ
    -0.07
    ิà¸Ķ
    -0.07
    POSITIVE LOGITS
     is
    0.11
     adalah
    0.09
     can
    0.09
     are
    0.08
     has
    0.08
     είναι
    0.07
     have
    0.07
    es
    0.07
    ANNOT
    0.07
     likely
    0.07
    Activations Density 0.228%

    No Known Activations