© 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. 65432
    Prev
    Next
    INDEX
    Explanations

    coil(s)

    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
    ahkan
    -0.08
    åĴĮ大
    -0.07
    èĹ»
    -0.07
    黼
    -0.07
    åĮĹæĸ¹
    -0.07
    ,DB
    -0.07
    inqui
    -0.07
    μμα
    -0.07
    chemist
    -0.07
    éĢĢæĪ¿
    -0.07
    POSITIVE LOGITS
    æĢ§çļ®çĤİ
    0.07
    oun
    0.07
    è¿Ļæł·çļĦäºĭæĥħ
    0.07
    æĢ§çļ®èĤ¤çĹħ
    0.07
    aka
    0.06
    .nd
    0.06
    åıijåĩºä¸Ģ
    0.06
    åĪ°å¤©
    0.06
    hod
    0.06
    -outline
    0.06
    Activations Density 0.050%

    No Known Activations