© 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. 62987
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ebo
    -0.08
    ycles
    -0.07
    egas
    -0.07
    ecycle
    -0.07
    idas
    -0.07
     chains
    -0.07
    tees
    -0.07
    ycle
    -0.07
    ariant
    -0.07
    heads
    -0.07
    POSITIVE LOGITS
    agram
    0.07
    uale
    0.07
    acruz
    0.07
    pel
    0.06
    æ°¸å®ī
    0.06
    ÑĢк
    0.06
    uha
    0.06
    ä¸ĢåĪ°
    0.06
    åıĮæµģ
    0.06
    паÑĤ
    0.06
    Activations Density 0.000%

    No Known Activations