© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 48397
    Prev
    Next
    INDEX
    Explanations

    year old, above, more

    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
    ÑģÑı
    -0.12
    ookie
    -0.10
    ojis
    -0.09
    aison
    -0.08
    aster
    -0.08
    ×ķ×IJ
    -0.08
    ำ
    -0.08
    <|box_end|>
    -0.08
    ä¼Ĭå§ĭ
    -0.08
    ÑĮÑı
    -0.08
    POSITIVE LOGITS
    entifier
    0.10
    s
    0.07
    ,
    0.07
    "
    0.07
    ì¦ĿìĿĦ
    0.07
    t
    0.07
    ers
    0.07
    erk
    0.07
    (
    0.06
    ë¡ľëĬĶ
    0.06
    Activations Density 0.002%

    No Known Activations