© 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. 61322
    Prev
    Next
    INDEX
    Explanations

    quantities or counts

    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
    æĺĮ
    -0.08
    ugn
    -0.07
    æī¿è®¤
    -0.07
    lava
    -0.07
    .gs
    -0.07
    ewe
    -0.07
    ecker
    -0.07
    ç»Ŀ大å¤ļæķ°
    -0.07
    -describedby
    -0.07
    iman
    -0.06
    POSITIVE LOGITS
    åĬłåĢį
    0.13
    ç¿»åĢį
    0.11
     doubled
    0.11
     halves
    0.11
     half
    0.11
     twice
    0.10
    åı¦ä¸ĢåįĬ
    0.10
    half
    0.10
     duplicated
    0.10
    åıĮåĢį
    0.10
    Activations Density 0.157%

    No Known Activations