© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 23490
    Prev
    Next
    INDEX
    Explanations

    technical configuration

    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
    ieste
    -0.08
    venient
    -0.07
     Stafford
    -0.06
    tep
    -0.06
    /rfc
    -0.06
    飶
    -0.06
    oare
    -0.06
     tact
    -0.06
    社
    -0.06
    bane
    -0.06
    POSITIVE LOGITS
     combination
    0.14
     combinations
    0.14
    ç»ĦåIJĪ
    0.14
    ä¸īèĢħ
    0.12
     Combination
    0.12
     Kombin
    0.12
    çµĦãģ¿åIJĪãĤıãģĽ
    0.12
    çļĦç»ĦåIJĪ
    0.11
     kombin
    0.11
     Kombination
    0.11
    Activations Density 0.165%

    No Known Activations