© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 9009
    Prev
    Next
    INDEX
    Explanations

    point after words like injection, defects, emission

    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
    tings
    -0.08
    conds
    -0.08
    łíĮ
    -0.08
    ilah
    -0.08
    åIJĦè¡Į
    -0.07
    verg
    -0.07
    åĴĮéĶĢåĶ®
    -0.07
    estern
    -0.07
    åİŁåĪĽæĸĩç«ł
    -0.07
    è®©æĽ´å¤ļçļĦ
    -0.07
    POSITIVE LOGITS
    æĪĸå°ı
    0.13
    /small
    0.11
    çĬ¶çļĦ
    0.09
    çĬ¶
    0.09
    ToPoint
    0.08
    /mobile
    0.08
    æĪĸå¤ļ
    0.08
    ish
    0.07
    -ish
    0.07
     halinde
    0.07
    Activations Density 0.034%

    No Known Activations