© 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. 40723
    Prev
    Next
    INDEX
    Explanations

    age of onset

    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
    stu
    -0.07
    çĶŁæķĪä¹ĭæĹ¥èµ·
    -0.07
    st
    -0.07
    itse
    -0.06
    ziger
    -0.06
    LLU
    -0.06
    ops
    -0.06
    å¥ĭæĸĹçļĦ
    -0.06
    ¿
    -0.06
    Ticks
    -0.06
    POSITIVE LOGITS
    æķħæѤ
    0.07
    æijĦ
    0.07
    ä»»åĩŃ
    0.07
    令ä»ĸ
    0.07
    =in
    0.07
    人äºĨ
    0.07
    _heading
    0.07
    inna
    0.07
    èĦĨ
    0.06
    å½ķ
    0.06
    Activations Density 0.021%

    No Known Activations