© 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. 60750
    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
    uluh
    -0.08
    peror
    -0.07
    ä¹Łä¸įä¾ĭå¤ĸ
    -0.07
     tally
    -0.06
    .displayName
    -0.06
    MinMax
    -0.06
    ç³Ļ
    -0.06
    oly
    -0.06
    ¤íĹ
    -0.06
    ovah
    -0.06
    POSITIVE LOGITS
     whatever
    0.08
    主è¦ģæĺ¯æĮĩ
    0.07
    ÐĹÐŀ
    0.07
    sir
    0.07
    åĨī
    0.07
    æŃ£æĸĩ
    0.07
    çĨŁ
    0.07
    SAT
    0.06
     deserialize
    0.06
     baile
    0.06
    Activations Density 0.000%

    No Known Activations