© 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. 23069
    Prev
    Next
    INDEX
    Explanations

    running build-heap algorithm

    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
    IGA
    -0.07
    è¿ĻäºĽä¸ľè¥¿
    -0.07
    ä¼
    -0.07
    ----------------------------------------------------------------------------
    -0.07
    ä»·æł¼ä¾¿å®ľ
    -0.07
    å¦Īå¦Ī们
    -0.06
     fuite
    -0.06
    igas
    -0.06
     measures
    -0.06
     measuring
    -0.06
    POSITIVE LOGITS
    æ¼Ķ示
    0.08
     walkthrough
    0.08
     dérou
    0.08
     recount
    0.08
    éĢIJ
    0.08
     timeline
    0.08
    触åıij
    0.08
     activations
    0.08
     sequence
    0.08
    æµģç¨ĭ
    0.08
    Activations Density 0.016%

    No Known Activations