© 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. 31712
    Prev
    Next
    INDEX
    Explanations

    Let be

    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
    è¿Ļæł·ä¸ĢæĿ¥
    -0.07
    ä»¥ä¹łè¿ijå¹³åIJĮå¿Ĺä¸ºæł¸å¿ĥçļĦåħļä¸Ń央
    -0.07
    abi
    -0.06
    æĺ¯æľ¬
    -0.06
    pers
    -0.06
    å¿
    -0.06
    çĶ³
    -0.06
    XXX
    -0.06
    abis
    -0.06
    ä¿¡éĺ³
    -0.06
    POSITIVE LOGITS
    åı¯éĢīä¸Ń
    0.08
    ãĤ»ãĥŁ
    0.08
    èĬ¸
    0.08
    RESSED
    0.07
    yny
    0.07
    ysel
    0.07
     Lets
    0.07
    omini
    0.07
    ussian
    0.07
    rooms
    0.07
    Activations Density 0.001%

    No Known Activations