© 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. 17282
    Prev
    Next
    INDEX
    Explanations

    attempting to install or load

    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
    aros
    -0.08
    åħ¬çĦ¶
    -0.07
    é¢Ĩè¡Ķ
    -0.07
    orni
    -0.07
    /latest
    -0.07
    retto
    -0.07
    ToEnd
    -0.07
    sse
    -0.07
    ä¹Łåı¯ä»¥æĺ¯
    -0.07
    InThe
    -0.06
    POSITIVE LOGITS
    请ç¨įåĢĻ
    0.10
    请ç¨į
    0.09
    æĺ¥æ±Ł
    0.08
    ...\
    0.07
    noinspection
    0.07
     Dump
    0.07
    paring
    0.07
     again
    0.07
    æ¶ķ
    0.07
    ÙĦاÙĤ
    0.07
    Activations Density 0.101%

    No Known Activations