© 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. 62308
    Prev
    Next
    INDEX
    Explanations

    rearrangement

    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
    à§Ģয়
    -0.11
    ëģĶ
    -0.10
    новен
    -0.10
    zelfde
    -0.09
    yiz
    -0.09
    ëĭ¥
    -0.09
    å®ŀå¤Ħ
    -0.09
    ÑģÑĤина
    -0.09
    ionario
    -0.09
    à¸Ĺัย
    -0.09
    POSITIVE LOGITS
    er
    0.09
    ments
    0.09
    åĴĮ
    0.09
    ly
    0.08
    ish
    0.08
    0.07
    ë¡ľ
    0.07
    ↵↵
    0.07
    اÙĭ
    0.07
    ↵
    0.06
    Activations Density 0.006%

    No Known Activations