© 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. 14190
    Prev
    Next
    INDEX
    Explanations

    asking 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
    ç»ıèIJ¥çIJĨ念
    -0.07
    _scheme
    -0.07
     Sons
    -0.07
    åĪĨ享åĨħ容
    -0.07
    åĨħ容æıIJä¾Ľæĸ¹
    -0.07
    urus
    -0.06
    ä¸ļ
    -0.06
    ector
    -0.06
    obuf
    -0.06
    iria
    -0.06
    POSITIVE LOGITS
    éĻIJå®ļ
    0.10
     wording
    0.08
     sekalipun
    0.08
    omo
    0.07
     asking
    0.07
    åĶĩ
    0.07
    ×£
    0.07
     asked
    0.07
    è¯Ńå¢ĥ
    0.07
     awak
    0.07
    Activations Density 0.005%

    No Known Activations