© 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. 65307
    Prev
    Next
    INDEX
    Explanations

    auto increment unique ids

    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
    æľĢ令人
    -0.08
    estos
    -0.08
     ÑĩÑĥ
    -0.08
    upu
    -0.08
    amina
    -0.08
    ungsver
    -0.08
    ?”,
    -0.08
    দà§į
    -0.08
    .moves
    -0.07
    路西
    -0.07
    POSITIVE LOGITS
    eld
    0.07
    ate
    0.06
    ä¾ĭå¦Ĥ
    0.06
    ä¼ģ
    0.06
    ä¸Ģå¼ı
    0.06
    ogra
    0.06
    ฯ
    0.06
    å°Ŀ
    0.06
    å¦Ĥæĺ¯
    0.06
    èĤĺ
    0.06
    Activations Density 0.020%

    No Known Activations