© 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. 1617
    Prev
    Next
    INDEX
    Explanations

    theory or hypothesis

    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
     kri
    -0.07
    çĥ¨
    -0.07
    uchi
    -0.06
     decep
    -0.06
     heartbreaking
    -0.06
    ahoma
    -0.06
    ìĺµ
    -0.06
    åĪĩä¸įåı¯
    -0.06
    .Physics
    -0.06
    èĩªè¨Ģ
    -0.06
    POSITIVE LOGITS
    åĪĻ认为
    0.19
    认为
    0.16
    ä¸»å¼ł
    0.15
    è§ĤçĤ¹
    0.14
    认为æĺ¯
    0.13
    çļĦè§ĤçĤ¹
    0.13
    éĥ½è®¤ä¸º
    0.13
    èªįçĤº
    0.13
    主張
    0.13
    ä»ĸ们认为
    0.11
    Activations Density 0.170%

    No Known Activations