© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 30037
    Prev
    Next
    INDEX
    Explanations

    vanishing bone disease

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    anvas
    -0.10
    WARDS
    -0.09
     ulang
    -0.09
    urally
    -0.08
    wards
    -0.08
    urop
    -0.08
    ê°±
    -0.07
    usch
    -0.07
    manship
    -0.07
    人æĿ¥è¯´
    -0.07
    POSITIVE LOGITS
    ishing
    0.12
    æ®Ĩå°½
    0.10
    es
    0.09
    /null
    0.09
    ç¢į
    0.08
    aby
    0.08
    ishes
    0.08
    ished
    0.08
    ible
    0.08
    ç¼¥ç¼Ī
    0.08
    Activations Density 0.007%

    No Known Activations