© 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. 8412
    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
    odont
    -0.07
    åħĨ
    -0.07
     seper
    -0.07
    ippets
    -0.07
    ip
    -0.06
    æĪijçıŃ
    -0.06
    åIJİç»ı
    -0.06
    é³Į
    -0.06
    便
    -0.06
    ak
    -0.06
    POSITIVE LOGITS
    èĩªè§īåľ°
    0.08
    æ·±æ·±åľ°
    0.08
    oen
    0.07
    Õ¸ÖĤÕ¶
    0.07
    (cp
    0.07
    è¦ĥ
    0.07
    éĹĨ
    0.07
    Ø·ÙĬÙĨ
    0.07
    uplic
    0.07
    尼奥
    0.07
    Activations Density 0.000%

    No Known Activations