© 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. 50705
    Prev
    Next
    INDEX
    Explanations

    discussion, review, characteristics, properties

    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
    ä¸įæĺ¯åIJĹ
    -0.08
    åĽłæŃ¤åľ¨
    -0.07
    _DIRECT
    -0.07
    缴æݥ被
    -0.07
    fang
    -0.07
    åĦ¿
    -0.07
    说åIJ§
    -0.06
    olda
    -0.06
    æĺ¯åIJ§
    -0.06
    ...
    -0.06
    POSITIVE LOGITS
    åIJĮæŶå°Ĩ
    0.09
    çĦ¶åIJİå°Ĩ
    0.09
    åIJĮæĹ¶å¯¹
    0.08
    æĢ§ä»¥åıĬ
    0.08
    åIJĮæŶè¦ģ
    0.08
    åIJĮæĹ¶ä¹Łè¦ģ
    0.08
     serta
    0.08
    åĬĽæ±Ĥ
    0.08
    çĿĢéĩį
    0.08
    并注æĦı
    0.08
    Activations Density 0.006%

    No Known Activations