© 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. 49804
    Prev
    Next
    INDEX
    Explanations

    characteristics and occupations

    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°±åľ¨è¿ĻéĩĮ
    -0.07
     both
    -0.07
    both
    -0.07
    姬
    -0.07
     TS
    -0.07
    åĪ°èĢģ
    -0.07
    gir
    -0.07
    azel
    -0.07
    er
    -0.07
    çŃ
    -0.07
    POSITIVE LOGITS
    anski
    0.07
    ุà¸ĩ
    0.07
    evo
    0.07
    aturi
    0.07
    avia
    0.07
    adf
    0.07
    æŃĮæĽ²
    0.07
    thes
    0.07
    è¿ĶåĽŀ顶éĥ¨
    0.07
    зов
    0.07
    Activations Density 0.148%

    No Known Activations