© 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. 38130
    Prev
    Next
    INDEX
    Explanations

    brisbane, ivermectin, philosophy

    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
    anit
    -0.08
    noinspection
    -0.08
    룴
    -0.08
    ersp
    -0.08
    hafen
    -0.07
    alde
    -0.07
    æĦıçļĦ
    -0.07
    çĻ¾æĪĺ
    -0.07
    esen
    -0.07
    züg
    -0.07
    POSITIVE LOGITS
    åĴĮ
    0.20
    à¸Ĺีà¹Ī
    0.13
    ãĤĴ
    0.13
    ë¡ľ
    0.12
    ной
    0.12
    ой
    0.10
    ìĻĢ
    0.10
    åĴĮæľīåħ³
    0.10
    åĴĮçĪ¶æ¯į
    0.10
    ìĹIJ
    0.09
    Activations Density 2.465%

    No Known Activations