© 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. 29999
    Prev
    Next
    INDEX
    Explanations

    water abstraction, win, appointment, transaction, fluid, withdrawn

    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
    interp
    -0.07
    æĹ¥æ¸¸
    -0.07
    ัà¸ģ
    -0.07
    @include
    -0.07
    onie
    -0.06
    }//
    -0.06
    ancier
    -0.06
    plic
    -0.06
    åĨįåĪ©çĶ¨
    -0.06
    .find
    -0.06
    POSITIVE LOGITS
    使å¾Ĺ
    0.13
    ä¼ļ使
    0.12
    ä»İèĢĮ使
    0.11
    使
    0.11
    å°Ĩ使
    0.11
    导èĩ´
    0.11
     waardoor
    0.11
     resulting
    0.10
     wodurch
    0.10
    èĩ´ä½¿
    0.10
    Activations Density 0.126%

    No Known Activations