© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 38960
    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
    izens
    -0.08
    strup
    -0.08
    bero
    -0.08
    etés
    -0.08
    rain
    -0.08
    tle
    -0.08
    liest
    -0.08
    tori
    -0.08
    é£İä¸Ń
    -0.07
    FFE
    -0.07
    POSITIVE LOGITS
    oenix
    0.09
    orus
    0.08
    ollower
    0.07
    ased
    0.07
    alcon
    0.07
    адÑĮ
    0.07
    cast
    0.07
    leg
    0.07
    atic
    0.07
    èĬĤçļĦ
    0.07
    Activations Density 0.075%

    No Known Activations