© 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. 30392
    Prev
    Next
    INDEX
    Explanations

    time references

    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
    åį³æĹ¥èµ·èĩ³
    -0.08
     tomorrow
    -0.08
    onsel
    -0.08
    她çİ°åľ¨
    -0.08
     tonight
    -0.07
     increasingly
    -0.07
    æľ¬åĪ¤åĨ³
    -0.07
    dessen
    -0.07
    ây
    -0.07
    æĸ°ãģŁãģ«
    -0.07
    POSITIVE LOGITS
    å½ĵæŶ
    0.16
    éĤ£æ¬¡
    0.15
    éĤ£æŶ
    0.14
    éĤ£æŶåĢĻ
    0.14
     damals
    0.14
    å½ĵæŶçļĦ
    0.14
    çķ¶æĻĤ
    0.13
    ä¹ŁæĽ¾
    0.12
    è¿ĩä¸Ģ次
    0.12
    éĤ£ä¸ªæŶåĢĻ
    0.12
    Activations Density 0.771%

    No Known Activations