© 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. 11680
    Prev
    Next
    INDEX
    Explanations

    I, my, now

    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
    Ø©
    -0.11
    <|box_end|>
    -0.10
    tä
    -0.10
    /or
    -0.10
    egration
    -0.08
    erior
    -0.08
    adays
    -0.08
    errupt
    -0.08
    entication
    -0.08
    ation
    -0.08
    POSITIVE LOGITS
    度çļĦ
    0.08
    ä¸Ģ个
    0.08
     inoltre
    0.07
    acent
    0.06
    ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
    0.06
    尤为
    0.06
    æĹ¢æľī
    0.06
    antin
    0.06
    illery
    0.06
    对äºİä¸Ģ个
    0.06
    Activations Density 0.039%

    No Known Activations