© 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. 4501
    Prev
    Next
    INDEX
    Explanations

    numbered lists and citations

    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
    ç½®
    -0.07
    ales
    -0.07
    -0.07
    ÅĻe
    -0.07
     ép
    -0.06
    订
    -0.06
    çļĦåIJĮåѦ
    -0.06
     Mab
    -0.06
    ally
    -0.06
    ÙĪعة
    -0.06
    POSITIVE LOGITS
    atsu
    0.09
    Prefs
    0.08
    é¤ħ
    0.08
    è½
    0.08
     Franken
    0.08
    è¯ķçĶ¨
    0.08
    argout
    0.08
    inya
    0.07
    ãĥijãĤ¤
    0.07
    ouden
    0.07
    Activations Density 0.916%

    No Known Activations