© 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. 28927
    Prev
    Next
    INDEX
    Explanations

    names following numbers or "reviews"

    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
    -0.08
    ickets
    -0.07
    $$
    -0.07
    áŀĽ
    -0.07
    ÑģÑĤеÑĢ
    -0.07
    ÑĪÑĤей
    -0.07
    коли
    -0.07
    rotch
    -0.07
    ίδ
    -0.07
    å®Ŀå±±
    -0.07
    POSITIVE LOGITS
    壮
    0.07
    å¦ĤåĽł
    0.07
    oup
    0.07
     Unused
    0.06
    壯
    0.06
    orz
    0.06
     reim
    0.06
    åIJĦçıŃ
    0.06
    ä¸įæĺ¯ä¸ºäºĨ
    0.06
    oun
    0.06
    Activations Density 0.037%

    No Known Activations