© 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. 60235
    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
    aphore
    -0.08
    aina
    -0.08
    awah
    -0.08
    onis
    -0.08
    зади
    -0.08
    ensburg
    -0.07
    ÏģÏİ
    -0.07
    uzione
    -0.07
    onnier
    -0.07
    onton
    -0.07
    POSITIVE LOGITS
    ji
    0.07
    大æŀĹ
    0.07
    ct
    0.07
    æ»´
    0.06
    ill
    0.06
    dro
    0.06
    aul
    0.06
    ja
    0.06
    il
    0.06
     paragraphs
    0.06
    Activations Density 0.000%

    No Known Activations