© 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. 38073
    Prev
    Next
    INDEX
    Explanations

    allocated, response, Chicago, specimen, users, unit

    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
    çĤĴ
    -0.07
    kana
    -0.06
    _NC
    -0.06
    umine
    -0.06
    zv
    -0.06
    ãģĨãģ¡
    -0.06
    ç´ł
    -0.06
    sula
    -0.06
    cima
    -0.06
    廳
    -0.06
    POSITIVE LOGITS
    没æľīéĤ£ä¹Ī
    0.08
    μαν
    0.08
    æĬķèµĦæĪĸ
    0.08
    åIJĪçIJĨåľ°
    0.08
    amat
    0.08
    lau
    0.07
    èĬ±åľ¨
    0.07
    ANG
    0.07
    ahir
    0.07
    åĪ°åºķæĺ¯ä»Ģä¹Ī
    0.07
    Activations Density 0.003%

    No Known Activations