© 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. 24501
    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
    дика
    -0.07
    纫
    -0.07
    æĶ¾çŁ¢
    -0.07
     sez
    -0.07
    æĥ¯æĢ§
    -0.07
    ãģ§ãģĻãĤĪ
    -0.07
    æķĪ
    -0.07
    pane
    -0.07
    så
    -0.06
    anium
    -0.06
    POSITIVE LOGITS
    icho
    0.07
    rose
    0.07
    rego
    0.07
    thin
    0.07
    éĽ¯
    0.07
    bo
    0.06
    rend
    0.06
     mon
    0.06
    èĸĦ
    0.06
     punch
    0.06
    Activations Density 0.000%

    No Known Activations