© 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. 62659
    Prev
    Next
    INDEX
    Explanations

    in fact

    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
    leta
    -0.08
    @(
    -0.08
     lesqu
    -0.08
    ãĥķãĥŃ
    -0.08
     Ristor
    -0.08
    .isValid
    -0.07
    çĦ¡åĬĽ
    -0.07
    YPE
    -0.07
    åIJĦå¼ıåIJĦ
    -0.07
    upe
    -0.07
    POSITIVE LOGITS
    ãģĻãĤī
    0.11
    ãĤĢãģĹãĤį
    0.10
    åıįèĢĮ
    0.10
     addirittura
    0.10
     malah
    0.09
    åıįèĢĮä¼ļ
    0.09
     sogar
    0.09
    çĶļèĩ³æľī
    0.09
    çĶļèĩ³
    0.09
     anzi
    0.09
    Activations Density 0.094%

    No Known Activations