© 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. 18744
    Prev
    Next
    INDEX
    Explanations

    glutamer, territory, omati, arness

    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
    æĥħåĨµåĪĨæŀIJ
    -0.07
    θά
    -0.06
    ISON
    -0.06
    enius
    -0.06
    ipp
    -0.06
    åħĭæĸ¯
    -0.06
     xoắn
    -0.06
    äºĨ她
    -0.06
    ége
    -0.06
    è¿ĻéĩĮæĺ¯
    -0.06
    POSITIVE LOGITS
    è±Ĩ
    0.07
    好å¤ļ
    0.07
    omatis
    0.07
    arness
    0.07
    <|box_end|>
    0.07
    unos
    0.07
    Ø·ÙĬب
    0.07
    ائع
    0.07
    å¾Īæ·±
    0.06
    пÑĢоÑĩем
    0.06
    Activations Density 0.003%

    No Known Activations