© 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. 28816
    Prev
    Next
    INDEX
    Explanations

    more than

    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
    ipse
    -0.10
    áĥ£áĥłáĥĺ
    -0.10
    ation
    -0.10
    ยà¸Ļà¸ķà¹Į
    -0.09
    IZAR
    -0.09
    æĶ¶èĹıæľ¬ç«Ļ
    -0.09
    Ø©
    -0.09
    มà¹Į
    -0.09
    สà¹Į
    -0.09
    entication
    -0.09
    POSITIVE LOGITS
    -than
    0.14
    mals
    0.13
    _than
    0.12
    erer
    0.12
    ened
    0.11
     than
    0.11
    heits
    0.10
     allá
    0.10
    than
    0.09
    _THAN
    0.09
    Activations Density 0.146%

    No Known Activations