© 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. 17974
    Prev
    Next
    INDEX
    Explanations

    strand or thread

    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
    imum
    -0.09
    urator
    -0.08
    ILED
    -0.08
    æĹłéĹ»
    -0.07
    lander
    -0.07
    ledged
    -0.07
    IVATE
    -0.07
    lectic
    -0.07
    ussion
    -0.07
    .appspot
    -0.07
    POSITIVE LOGITS
    edly
    0.10
    wise
    0.10
    iness
    0.10
    iversary
    0.08
    less
    0.08
    korb
    0.08
    arring
    0.08
    ä¸ĬçļĦ
    0.08
    دÙĬØ©
    0.08
    åĦ¿
    0.08
    Activations Density 0.030%

    No Known Activations