© 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. 51684
    Prev
    Next
    INDEX
    Explanations

    that case

    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
     mãi
    -0.07
    ional
    -0.07
    iskus
    -0.06
    åĵ¦
    -0.06
    creens
    -0.06
    çļĦä¸Ģ项
    -0.06
    eware
    -0.06
    urname
    -0.06
    çļĦä¸Ģ大
    -0.06
    chemas
    -0.06
    POSITIVE LOGITS
    æĥħåĨµä¸ĭ
    0.10
     latter
    0.09
     ÑģлÑĥÑĩае
    0.09
    ikian
    0.09
     case
    0.08
    èµ·è§ģ
    0.08
    جا
    0.08
    åł´åIJĪ
    0.08
    çĬ¶æĢģä¸ĭ
    0.08
     regard
    0.08
    Activations Density 0.051%

    No Known Activations