© 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. 24806
    Prev
    Next
    INDEX
    Explanations

    if and only if

    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
     trám
    -0.07
    imb
    -0.07
    以åIJİåĨį
    -0.07
    ULE
    -0.07
    éħ
    -0.06
    ikit
    -0.06
     expectativa
    -0.06
    uben
    -0.06
    DEFINE
    -0.06
    hir
    -0.06
    POSITIVE LOGITS
     iff
    0.12
    æĺ¯åIJ¦
    0.10
    ä¸İåIJ¦
    0.10
    ä»Ģä¹ĪæŶåĢĻ
    0.10
    èĥ½åIJ¦
    0.09
     whether
    0.09
    _iff
    0.09
    å¦Ĥæŀľæĥ³
    0.09
    ä¹ĭæīĢ以
    0.09
    ä½ķæŶ
    0.09
    Activations Density 0.050%

    No Known Activations