© 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. 31156
    Prev
    Next
    INDEX
    Explanations

    "i" questions

    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
    ¬
    -0.06
    ambi
    -0.06
    å±ħæĺĵ
    -0.06
     ìķĦëĭĪë©´
    -0.06
    rases
    -0.06
    orex
    -0.06
    åĨįçľĭçľĭ
    -0.06
     ë°ĺëĵľìĭľ
    -0.06
    ä»ĭ
    -0.05
    å·§
    -0.05
    POSITIVE LOGITS
     conclu
    0.08
    çľĭå¾ĹåĩºæĿ¥
    0.08
    ayos
    0.08
    çļĦå¿ĥçģµ
    0.07
    åı¯ä»¥çľĭåĩº
    0.07
    以ä¸Ĭãģ®
    0.07
    èĪįå¾Ĺ
    0.07
    ãģ¾ãģ¨ãĤģ
    0.07
    artz
    0.07
    ormap
    0.07
    Activations Density 0.001%

    No Known Activations