© 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. 43153
    Prev
    Next
    INDEX
    Explanations

    ## followed by word

    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
    ç½ijå°ıç¼ĸ
    -0.08
    chado
    -0.08
    estream
    -0.08
    çī¹æľĹ
    -0.08
     tenden
    -0.08
     gede
    -0.08
    ждÑĭ
    -0.07
    ¤í
    -0.07
    çļĦç½ijåıĭ
    -0.07
    anjang
    -0.07
    POSITIVE LOGITS
    terra
    0.08
    ä¸ĢåĪĩéĥ½æĺ¯
    0.07
    ça
    0.06
    protobuf
    0.06
    tä
    0.06
    adne
    0.06
    ãģ«ãģĤ
    0.06
     dur
    0.06
    åĪ«æĹł
    0.06
    æ±²
    0.06
    Activations Density 0.007%

    No Known Activations