© 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. 40038
    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
    è¸
    -0.07
    褥
    -0.07
    aik
    -0.06
    PO
    -0.06
    AdapterFactory
    -0.06
     comod
    -0.06
    Ø´ÙĨ
    -0.06
    orf
    -0.06
    edor
    -0.06
    èĩªå¦Ĥ
    -0.06
    POSITIVE LOGITS
    çĪĨçł´
    0.06
    ichier
    0.06
    isar
    0.06
    ä¸Ģå±Ģ
    0.06
     evolving
    0.06
    å¼ķ人åħ¥
    0.06
    éŨè¯Ĭéĥ¨
    0.06
    ondre
    0.06
    apu
    0.06
    adian
    0.06
    Activations Density 0.000%

    No Known Activations