© 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. 18075
    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
    ẩu
    -0.09
    .navigator
    -0.09
    antina
    -0.09
    evers
    -0.09
    ampak
    -0.09
    ieties
    -0.08
     ratus
    -0.08
    Stats
    -0.08
    isEqual
    -0.08
    azzur
    -0.08
    POSITIVE LOGITS
     co
    0.07
    ↵↵
    0.06
    .
    0.06
    __
    0.06
    ↵
    0.06
     coh
    0.06
    ç´§æī£
    0.06
    's
    0.06
     ident
    0.06
    String
    0.06
    Activations Density 0.000%

    No Known Activations