© 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. 18261
    Prev
    Next
    INDEX
    Explanations

    name entity recognition

    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
    è¿Ļ便æĺ¯
    -0.08
    è¿ĺåºĶå½ĵ
    -0.08
    agger
    -0.08
     ÐĹаÑĤо
    -0.08
    è¿ĶåĽŀ顶éĥ¨
    -0.08
    ostos
    -0.07
    efore
    -0.07
    åĪ«å¿ĺäºĨ
    -0.07
    åį´èĥ½
    -0.07
    åĨįæİ¥åĨįåİī
    -0.07
    POSITIVE LOGITS
    æĺ¯åIJ§
    0.08
    ç®Ģ称
    0.07
    天å®ĩ
    0.07
    >>>>>>>
    0.07
    对åIJ§
    0.06
    Ïģα
    0.06
    -svg
    0.06
    éĢļ常
    0.06
    umably
    0.06
    常è§ģçļĦ
    0.06
    Activations Density 0.127%

    No Known Activations