© 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. 23864
    Prev
    Next
    INDEX
    Explanations

    greeting, introduction, and discussion topic

    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
    æħ§èģªç½ij
    -0.08
    ajari
    -0.08
    aversal
    -0.07
    è¿ĻæŶ
    -0.07
    è¦ģå°ıå¿ĥ
    -0.07
    ascin
    -0.07
    å®ĺæĸ¹åįļ客
    -0.07
    LATED
    -0.07
    ä¸įè¿ĺ
    -0.07
    ///<
    -0.07
    POSITIVE LOGITS
    otel
    0.07
     ideally
    0.06
    kok
    0.06
    ami
    0.06
    çº¾åĽ°
    0.06
    astien
    0.06
    ðĿ
    0.06
    åħĥå®ĩå®Ļ
    0.06
    å°ıèĬĤ
    0.06
    bs
    0.06
    Activations Density 0.136%

    No Known Activations