© 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. 12407
    Prev
    Next
    INDEX
    Explanations

    necessitates, helped, we, be, not, stock

    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
     apparently
    -0.08
    å¾Īå¥ĩæĢª
    -0.07
    ockey
    -0.07
     (=
    -0.06
     (
    -0.06
    (?)
    -0.06
     very
    -0.06
    使人
    -0.06
      ↵
    -0.06
    èĦ±ç¦»
    -0.06
    POSITIVE LOGITS
     [âĢ¦
    0.14
     [âĢ¦]
    0.12
    éĥ½èĥ½å¤Ł
    0.10
    [âĢ¦
    0.10
    âĢ¦..
    0.09
     healthcare
    0.08
    éļıçĿĢæŶéĹ´çļĦæݨ移
    0.08
    以ä¸ĭæĺ¯ä¸ĢäºĽ
    0.08
    åı¯è°ĵæĺ¯
    0.08
    **–
    0.08
    Activations Density 0.342%

    No Known Activations