© 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. 34657
    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
    {/
    -0.07
    wah
    -0.07
    çĶ¨æĸĻ
    -0.07
     matters
    -0.06
    åĪĨåĪ«æĺ¯
    -0.06
    ä¸įä¼ļæľī
    -0.06
    regel
    -0.06
     Leb
    -0.06
    ils
    -0.06
    iers
    -0.06
    POSITIVE LOGITS
    izzle
    0.07
    Ư
    0.07
    .shows
    0.07
    acro
    0.07
    irty
    0.07
    uerta
    0.07
    жаÑĤ
    0.07
    æľªåıĬæŶ
    0.07
    CRET
    0.07
    绾
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.