© 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. 10369
    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
    åį¸
    -0.07
    urgeon
    -0.07
    æŁ¥çľĭåħ¨éĥ¨
    -0.07
    oyo
    -0.07
     nostalg
    -0.07
    wort
    -0.07
    ä¸Ńç²®
    -0.07
    ÏĦÏģια
    -0.07
    jaw
    -0.07
    æľ¬åľºæ¯ĶèµĽ
    -0.07
    POSITIVE LOGITS
    èĦĬ
    0.08
    ible
    0.07
    helpers
    0.06
    untime
    0.06
    严
    0.06
    odom
    0.06
    æ¥
    0.06
    .literal
    0.06
    srv
    0.06
    西æ¹ĸ
    0.06
    Activations Density 0.000%

    No Known Activations