© 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. 19578
    Prev
    Next
    INDEX
    Explanations

    venous obstruction or insufficiency

    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
     Sérgio
    -0.07
     impre
    -0.07
    èģĺ
    -0.07
    aru
    -0.07
     ÑĪÑĤÑĥка
    -0.07
    ãĥ³ãĥĪãĥ³
    -0.07
    -webpack
    -0.06
    oten
    -0.06
    kken
    -0.06
    grim
    -0.06
    POSITIVE LOGITS
    åĽŀæµģ
    0.11
    _flow
    0.09
     pooling
    0.08
    æµģåIJij
    0.08
    æĶ¯æµģ
    0.08
    港湾
    0.08
    ools
    0.08
    æ·¤
    0.08
     vessel
    0.08
     vessels
    0.08
    Activations Density 0.039%

    No Known Activations