© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 52086
    Prev
    Next
    INDEX
    Explanations

    mathematical function arguments

    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
    Negative Logits
    éĻµ
    -0.08
    éĻµåİ¿
    -0.07
    éļħ
    -0.07
    åħ®åħ®
    -0.07
    çľºæľĽ
    -0.07
    falt
    -0.07
    æĭīæĸ¯
    -0.07
    åī©ä½ĻçļĦ
    -0.06
    amac
    -0.06
    éĶ¦æ¶Ľ
    -0.06
    POSITIVE LOGITS
    ÙĨج
    0.07
    客ä½ĵ
    0.07
    åĩĨ
    0.07
    æĺŁåº§
    0.07
    yu
    0.07
    ×ķ×ķ
    0.07
    imba
    0.07
    lemn
    0.07
    cola
    0.07
    orp
    0.07
    Activations Density 0.017%

    No Known Activations