© 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. 25788
    Prev
    Next
    INDEX
    Explanations

    start of informative clauses

    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
     lidi
    -0.07
    èĥŀèĥİ
    -0.07
    ãģĹãĤį
    -0.07
    -called
    -0.07
    纳德
    -0.07
    apers
    -0.06
    arcer
    -0.06
    TYPES
    -0.06
     shiny
    -0.06
    ãĥĥãĥī
    -0.06
    POSITIVE LOGITS
    ÃľR
    0.07
    olith
    0.07
    祥
    0.07
    obuf
    0.07
    akarta
    0.07
    ÃģN
    0.07
    FRING
    0.07
    JOR
    0.07
    表ä¸Ń
    0.07
    loge
    0.07
    Activations Density 0.038%

    No Known Activations