© 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. 11582
    Prev
    Next
    INDEX
    Explanations

    from to

    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
    ulut
    -0.08
    onnen
    -0.07
    áÅĻ
    -0.07
    èī²åĪĹ
    -0.07
    utÄĥ
    -0.07
    olly
    -0.07
    isir
    -0.07
    ĶĦ
    -0.07
    ee
    -0.07
    ÑĢад
    -0.06
    POSITIVE LOGITS
    /from
    0.10
    ãģĹãģıãģ¯
    0.08
    /or
    0.08
    åĨįåĪ°
    0.08
    /of
    0.08
    ...
    0.08
     others
    0.07
    ...",
    0.07
    ä¸įäºĨ
    0.07
    æĺ¯ä¸įå¤Ł
    0.07
    Activations Density 0.078%

    No Known Activations