© 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. 34231
    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
    ç»ijæīİ
    -0.07
    luck
    -0.07
    Å¡ÃŃ
    -0.06
    bij
    -0.06
    山头
    -0.06
     ë°ľêµ´
    -0.06
     اÙĦÙĤب
    -0.06
    åĴĮ缮æłĩ
    -0.06
    cki
    -0.06
    éķ¿èĢģ
    -0.06
    POSITIVE LOGITS
    speed
    0.12
     speed
    0.11
     speeds
    0.11
     Speed
    0.10
    éĢŁåº¦
    0.10
    _speed
    0.10
    -Speed
    0.09
    -speed
    0.09
    peed
    0.09
    åħīéĢŁ
    0.09
    Activations Density 0.000%

    No Known Activations