© 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. 40412
    Prev
    Next
    INDEX
    Explanations

    looking for alternatives

    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
    pal
    -0.07
    .watch
    -0.06
    _optimizer
    -0.06
     bÃło
    -0.06
     geek
    -0.06
    åĽŀæĿ¥äºĨ
    -0.06
    _regression
    -0.06
     darin
    -0.06
    logger
    -0.06
    她就æĺ¯
    -0.06
    POSITIVE LOGITS
     instead
    0.13
    instead
    0.12
     Instead
    0.11
    Instead
    0.11
    æĶ¹æĪIJ
    0.11
    æĶ¹ä¸º
    0.11
     вмеÑģÑĤо
    0.10
    æĶ¹çĤº
    0.10
    _altern
    0.10
    ãĤĤãģĨå°ijãģĹ
    0.10
    Activations Density 0.193%

    No Known Activations