© 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. 11257
    Prev
    Next
    INDEX
    Explanations

    superscripts or mathematical notation

    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
    çļĦ
    -0.08
    nya
    -0.07
    를
    -0.07
    usul
    -0.07
    able
    -0.07
    ÛĮ
    -0.07
    iffs
    -0.07
    ankind
    -0.06
    à§ĩর
    -0.06
    CanBe
    -0.06
    POSITIVE LOGITS
    ä¸įåı¯æĢĿè®®
    0.10
    åĭĩå¾Ģ缴åīį
    0.09
    ness
    0.09
    身临åħ¶å¢ĥ
    0.08
    Ø©
    0.08
    缸è¾ħ缸æĪIJ
    0.08
    çļĦæŶéĹ´éĩĮ
    0.08
    ité
    0.08
    almart
    0.08
    ï¸İ
    0.08
    Activations Density 0.016%

    No Known Activations