© 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. 38953
    Prev
    Next
    INDEX
    Explanations

    numbers and dates

    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
    好åij¢
    -0.08
    å¦Ĥä¸ĭ
    -0.08
    çĶļèĩ³æĺ¯
    -0.07
    èĢĮéĢłæĪIJ
    -0.07
     riguardo
    -0.07
    *))
    -0.07
    æīĢè°ĵçļĦ
    -0.07
     appunto
    -0.06
    >:</
    -0.06
    åħ¶åİŁåĽł
    -0.06
    POSITIVE LOGITS
    åijĹ
    0.09
     vs
    0.08
    åIJĮä¸Ĭ
    0.08
    !!!!!!!!
    0.08
    æĿ¥åķ¦
    0.08
    ÑĤоÑĩнаÑı
    0.07
     λοι
    0.07
    æĮijæĪĺèµĽ
    0.07
    ogn
    0.07
     Same
    0.07
    Activations Density 0.055%

    No Known Activations