© 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. 24105
    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
    stvo
    -0.07
    ijnen
    -0.07
    retto
    -0.07
    ossen
    -0.07
    eggi
    -0.07
    ä¸Ĭæ·»
    -0.07
    ס×Ļ
    -0.07
    ¨
    -0.06
    åĩ«
    -0.06
    çĹ£
    -0.06
    POSITIVE LOGITS
    ÙĪÙĨØ©
    0.08
    hap
    0.07
    ardy
    0.07
    _TERMIN
    0.07
    gow
    0.07
    æĪIJéķ¿çļĦ
    0.07
    .Err
    0.07
    å¼Ħ
    0.07
    olos
    0.07
    ihar
    0.06
    Activations Density 0.000%

    No Known Activations