© 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. 34505
    Prev
    Next
    INDEX
    Explanations

    research paper template

    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
    ær
    -0.07
    æĪijçļĦç¥Ŀç¦ı
    -0.07
    ijnen
    -0.07
    æľ¬åºĹ
    -0.06
    æijĴ
    -0.06
    _NOTIFY
    -0.06
    éron
    -0.06
    _dispatch
    -0.06
    ä¹¾åĿ¤
    -0.06
    æķ¢è¯´
    -0.06
    POSITIVE LOGITS
    nios
    0.08
    æĢİä¹Ī
    0.07
    æĢİä¹Īåİ»
    0.07
    æľīèī²
    0.07
    åľĸçīĩ
    0.07
    å²ģéĤ£å¹´
    0.07
    ä»Ģä¹Īåľ°æĸ¹
    0.07
    çĤ¹ä»Ģä¹Ī
    0.07
    çĶ¨ä»Ģä¹Ī
    0.07
    æĢİä¹Īçľĭ
    0.07
    Activations Density 0.573%

    No Known Activations