© 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. 56919
    Prev
    Next
    INDEX
    Explanations

    future directions and challenges

    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
    åħ·æľī以ä¸ĭ
    -0.08
    æľī以ä¸ĭ
    -0.07
    vej
    -0.06
    æľīä¸ĭåĪĹæĥħå½¢ä¹ĭä¸ĢçļĦ
    -0.06
    çĬģ
    -0.06
    请ä¸ĭè½½
    -0.06
    bsp
    -0.06
     vagas
    -0.06
    Tmp
    -0.06
    èĤĨ
    -0.06
    POSITIVE LOGITS
    enni
    0.08
    æĪijçļĦçľĭæ³ķ
    0.08
    åıĹçļĦ
    0.07
    æĥħåĨµåıĬ
    0.07
     infine
    0.07
     ë§Īì§Ģë§īìľ¼ë¡ľ
    0.07
     enfin
    0.07
    è³¢
    0.07
    çŀ°
    0.07
     outlook
    0.07
    Activations Density 0.039%

    No Known Activations