© 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. 39333
    Prev
    Next
    INDEX
    Explanations

    middle-aged women""middle blessings""middle class" motel"middle ear surgery""Middle ear disease""middle point"

    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
    ÙĭÙijا
    -0.10
    RITE
    -0.10
    wander
    -0.10
    ãĥķãĤ©ãĥ³
    -0.10
    γά
    -0.10
    èĢĮä»ĸçļĦ
    -0.10
    å§ĭèĩ³ç»Ī
    -0.10
     ê²Įëĭ¤ê°Ģ
    -0.09
    schutz
    -0.09
    èrement
    -0.09
    POSITIVE LOGITS
    ìļĶ
    0.08
    0.07
    ↵
    0.07
    cy
    0.07
    “
    0.07
    2
    0.07
    د
    0.07
    çļĦ人æ°Ķ
    0.06
    1
    0.06
    ,
    0.06
    Activations Density 0.011%

    No Known Activations