© 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. 26008
    Prev
    Next
    INDEX
    Explanations

    cast as float or varchar

    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
    èĢģå®ŀ
    -0.07
    urat
    -0.07
    çĿĢåij¢
    -0.07
    乡åİ¿
    -0.07
    ç¬Ĩ
    -0.07
    çĿĢä»Ģä¹Ī
    -0.07
    æķĻèĤ²åĩºçīĪ社
    -0.07
    %c
    -0.07
    èĢ¸
    -0.07
    (Throwable
    -0.06
    POSITIVE LOGITS
    æħ¢æħ¢
    0.07
    _converter
    0.07
    gw
    0.07
    IOS
    0.07
    inded
    0.07
    .opensource
    0.06
    ishes
    0.06
    COMMENT
    0.06
    uard
    0.06
     اÙĦÙĬ
    0.06
    Activations Density 0.006%

    No Known Activations