© 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. 12875
    Prev
    Next
    INDEX
    Explanations

    train stations or routes

    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
    ToObject
    -0.08
    åħ¬åı¸åIJij
    -0.07
    起家
    -0.07
    çݯå¢ĥä¸İ
    -0.07
    åĨ²åĪ°
    -0.07
    åIJijåħļ
    -0.07
    ãĢıãĢİ
    -0.07
    ä¸Ģå¤ķ
    -0.07
     dazu
    -0.07
    å§ĭèĩ³
    -0.06
    POSITIVE LOGITS
    åĨįåĪ°
    0.15
    为æŃ¢
    0.13
     ÙĪØ¥ÙĦÙī
    0.12
    çļĦè¿ĩç¨ĭä¸Ń
    0.11
    çĤºæŃ¢
    0.09
    çļĦè·¯ä¸Ĭ
    0.09
    ä¹ĭæĹ¥æŃ¢
    0.09
    åĨįä»İ
    0.09
     via
    0.08
    éĢĶä¸Ń
    0.08
    Activations Density 0.040%

    No Known Activations