© 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. 14459
    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
    ovo
    -0.07
    mite
    -0.07
    udu
    -0.07
    ofi
    -0.07
    uos
    -0.06
    :<
    -0.06
    umos
    -0.06
    åīįèĢħ
    -0.06
    dale
    -0.06
    rement
    -0.06
    POSITIVE LOGITS
    âĢ
    0.07
    å¾ĭå·±
    0.07
    è¡
    0.07
    č
    0.07
    วะ
    0.06
     erotik
    0.06
    ất
    0.06
    èĢĮåĬ¨
    0.06
    reopen
    0.06
     köln
    0.06
    Activations Density 0.000%

    No Known Activations