© 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. 45909
    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
    åĩ¡äºĭ
    -0.07
    oram
    -0.06
    hir
    -0.06
    óch
    -0.06
    SCALL
    -0.06
    æ»ĭ
    -0.06
    éķ¿äºĨ
    -0.06
    erti
    -0.06
    æķĻèĤ²åѦçĶŁ
    -0.06
    çĶ¨æľĢ
    -0.06
    POSITIVE LOGITS
    upo
    0.09
    lero
    0.08
    缨
    0.08
    éĺĻ
    0.08
    çĴĩ
    0.08
    athers
    0.07
    лко
    0.07
    usche
    0.07
    folio
    0.07
    nul
    0.07
    Activations Density 0.000%

    No Known Activations