© 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. 60180
    Prev
    Next
    INDEX
    Explanations

    algorithms

    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
    åħĭåħ°
    -0.08
    åĽ´ç»ķ
    -0.07
    vil
    -0.07
    绣çŃ¹æİ¨è¿Ľ
    -0.07
    éĢĤåIJĪçļĦ
    -0.07
    linger
    -0.07
    NewProp
    -0.07
    ä¸İ交æµģ
    -0.07
     Jur
    -0.07
    ä¸ĵä¸ļ人åijĺ
    -0.07
    POSITIVE LOGITS
     already
    0.08
    ä¸įåľ¨
    0.08
    å·²ç»ı被
    0.08
    已被
    0.08
    enn
    0.07
    å·²çŁ¥
    0.07
    碰
    0.07
     previously
    0.07
     belonged
    0.07
     known
    0.07
    Activations Density 0.026%

    No Known Activations