© 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. 32474
    Prev
    Next
    INDEX
    Explanations

    numbers and quantities

    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
    ibold
    -0.09
    ]|[
    -0.09
    檬
    -0.08
    ÑģовеÑģÑĤ
    -0.08
    /single
    -0.08
    OLUMN
    -0.08
    umon
    -0.08
    irts
    -0.08
    heed
    -0.08
    ,total
    -0.08
    POSITIVE LOGITS
    0.08
     or
    0.07
    +
    0.06
    1
    0.06
    orso
    0.06
    èĥ¤
    0.06
    5
    0.06
     (!
    0.06
    ,
    0.06
    .
    0.05
    Activations Density 0.615%

    No Known Activations