© 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. 16373
    Prev
    Next
    INDEX
    Explanations

    what i want

    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
    alp
    -0.07
     ube
    -0.07
    plays
    -0.07
     íķĦ
    -0.06
    _DEF
    -0.06
    ätt
    -0.06
    bü
    -0.06
    ä»ĩ
    -0.06
    aos
    -0.06
    egl
    -0.06
    POSITIVE LOGITS
    ãģ¾ãģķãģ«
    0.08
    天äºĨ
    0.08
    ork
    0.08
    åıĺ缸
    0.07
     sort
    0.07
    å°±æĺ¯æĪij们çļĦ
    0.07
    ja
    0.07
    æĪijåIJĹ
    0.07
    ä¸įå°±æĺ¯
    0.07
    æŃ£æĺ¯
    0.07
    Activations Density 0.063%

    No Known Activations