© 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. 62125
    Prev
    Next
    INDEX
    Explanations

    process or analyze

    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
    çĶ¨ä»¥
    -0.09
    éĢļè¿ĩå°Ĩ
    -0.08
    çĶ¨æĿ¥
    -0.08
     graças
    -0.08
     considerably
    -0.08
    çļĦçī¹çĤ¹æĺ¯
    -0.07
     ÑĩÑĤобÑĭ
    -0.07
     infatti
    -0.07
     tellement
    -0.07
    éĢļè¿ĩåľ¨
    -0.07
    POSITIVE LOGITS
     appunto
    0.11
     Zwecke
    0.10
     sake
    0.10
     purposes
    0.10
     ×ķ׾×Ķ
    0.09
    åĴĮæĶ¹åĸĦ
    0.08
    åħ¶å¯¹
    0.08
     ×ķ׾
    0.08
    igy
    0.08
     ÑıкобÑĭ
    0.08
    Activations Density 0.501%

    No Known Activations