© 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. 50462
    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
    ungsver
    -0.09
     klo
    -0.08
    åd
    -0.08
    ег
    -0.08
     Monti
    -0.08
    venes
    -0.08
    bacher
    -0.08
    åŃ£çļĦ
    -0.07
    dorf
    -0.07
     Minist
    -0.07
    POSITIVE LOGITS
    çĥŃ
    0.07
    éĶ»
    0.06
    .cn
    0.06
     inter
    0.06
    åħ¥ç¾¤
    0.06
    èĦijåIJİ
    0.06
    è¡Ģ
    0.06
    buff
    0.06
    he
    0.06
    丧
    0.06
    Activations Density 0.000%

    No Known Activations