© 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. 42180
    Prev
    Next
    INDEX
    Explanations

    fossils and ancient discoveries

    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
    onas
    -0.07
    å¼ıä¸Ń
    -0.07
    åħ¼ä»»
    -0.07
    罩
    -0.07
    alli
    -0.07
    isser
    -0.07
     Svg
    -0.07
    æŁ¥çľĭåħ¨éĥ¨
    -0.06
     tailored
    -0.06
    ekyll
    -0.06
    POSITIVE LOGITS
    åĩºåľŁ
    0.12
    ä¿ĿåŃĺ
    0.11
     preserved
    0.11
     recovered
    0.10
     discovered
    0.10
     autent
    0.10
    åıijçİ°çļĦ
    0.10
    æ®ĭ缺
    0.10
     discoveries
    0.10
    åıijçİ°äºĨ
    0.10
    Activations Density 0.174%

    No Known Activations