© 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. 56994
    Prev
    Next
    INDEX
    Explanations

    epithelial

    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
    gage
    -0.08
    gers
    -0.08
    nable
    -0.08
    iau
    -0.07
    fuse
    -0.07
    íĥķ
    -0.07
    spot
    -0.07
     Rosenberg
    -0.07
    port
    -0.07
    spots
    -0.07
    POSITIVE LOGITS
    zellen
    0.10
    ç»Ĩèĥŀ
    0.10
     cells
    0.09
    ìĦ¸íı¬
    0.09
    elial
    0.09
    ç»ĨèĥŀçļĦ
    0.09
     franch
    0.08
    å±Ĥ
    0.08
    ä¸Ģè¡Į
    0.08
     epith
    0.08
    Activations Density 0.090%

    No Known Activations