© 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. 17708
    Prev
    Next
    INDEX
    Explanations

    convention. attracted. developed. used

    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
    ãģ¾ãģĽãĤĵãģĮ
    -0.08
    缸åħ³éĹ®çŃĶ
    -0.08
    ãģ®ãģĭãĤĤãģĹãĤĮ
    -0.08
    ãģĹãĤį
    -0.07
    ãģ§ãģĻãģĭãĤī
    -0.07
    æĿ¥ä¹ĭ
    -0.07
     Secr
    -0.07
    满åłĤ
    -0.07
     olup
    -0.07
     ìĹĨê³ł
    -0.07
    POSITIVE LOGITS
    pil
    0.06
    Äĩ
    0.06
    _protocol
    0.06
    itech
    0.06
    edly
    0.06
    analys
    0.06
     reper
    0.06
     //(
    0.06
    ç»ĻäºĨ
    0.06
    æľĢ为
    0.06
    Activations Density 0.048%

    No Known Activations