© 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. 14871
    Prev
    Next
    INDEX
    Explanations

    previous thread

    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
    为äºĨèĥ½
    -0.07
    空æ°Ķèĥ½
    -0.06
    è¿Ļä½į
    -0.06
    èĥ½çĶ¨
    -0.06
    kit
    -0.06
    empor
    -0.06
    ä¸Ģé¢Ĺ
    -0.06
    Kit
    -0.06
    lene
    -0.06
    çļĦæľīåĬĽ
    -0.06
    POSITIVE LOGITS
    å·²æľīçļĦ
    0.11
    (existing
    0.11
    æĹ¢åŃĺ
    0.10
    existing
    0.10
    _existing
    0.10
     précédente
    0.10
    Prev
    0.09
    Existing
    0.09
    -existing
    0.09
    çİ°æľīçļĦ
    0.09
    Activations Density 0.290%

    No Known Activations