© 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. 14460
    Prev
    Next
    INDEX
    Explanations

    young ones, interested people

    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
    ç»Ļ客æĪ·
    -0.08
    esten
    -0.08
    ä¼ģä¸ļèģĮå·¥
    -0.08
    ä¸ŃåĽ½å®¶
    -0.08
    Trader
    -0.07
    iaux
    -0.07
    Äiju
    -0.07
    laub
    -0.07
    è¦ģæ±ĤåIJĦ
    -0.07
    ç»Ļå®Ŀå®Ŀ
    -0.07
    POSITIVE LOGITS
     who
    0.09
    who
    0.08
    人对
    0.08
    ìĹIJê²Į
    0.08
    ä½łåij¢
    0.08
     interested
    0.08
    人éĥ½
    0.08
     whoever
    0.07
     quien
    0.07
     young
    0.07
    Activations Density 1.047%

    No Known Activations