© 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. 23684
    Prev
    Next
    INDEX
    Explanations

    recommending actions or changes

    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
     magically
    -0.07
    æĪij们å¿ħé¡»
    -0.07
    æĺ¯éĽĨ
    -0.07
    æĪijå¿ħé¡»
    -0.07
     apparently
    -0.07
    éľĢæıIJä¾Ľ
    -0.07
     باÙĦض
    -0.07
     supposedly
    -0.07
    ĵ¨
    -0.07
    æĪij们éľĢè¦ģ
    -0.07
    POSITIVE LOGITS
    enever
    0.10
     whenever
    0.10
    èĩ³å°ij
    0.09
     almeno
    0.09
     поÑĩа
    0.09
    å°½éĩıéģ¿åħį
    0.08
    ä¸į建议
    0.08
     anytime
    0.08
     avoid
    0.08
    ä¸įè¦ģè½»æĺĵ
    0.08
    Activations Density 0.393%

    No Known Activations