© 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. 31838
    Prev
    Next
    INDEX
    Explanations

    logistic regression

    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
    abar
    -0.06
    ç«ĭ足
    -0.06
     jedenfalls
    -0.06
    åıĬåIJĦç§į
    -0.06
    xia
    -0.06
    udur
    -0.06
    å®ļ
    -0.06
    iber
    -0.06
     Tot
    -0.06
     tag
    -0.06
    POSITIVE LOGITS
    åħ¶ä»ĸ
    0.13
    åħ¶ä»ĸçļĦ
    0.13
    åħ¶ä»ĸ人çļĦ
    0.12
    çļĦåħ¶ä»ĸ
    0.12
    åħ¶å®ĥçļĦ
    0.12
    åħ¶å®ĥ
    0.11
    åħ¶ä»ĸ人
    0.11
     other
    0.11
     оÑģÑĤалÑĮнÑĭÑħ
    0.11
    ä»»ä½ķåħ¶ä»ĸ
    0.11
    Activations Density 0.105%

    No Known Activations