© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17890
    Prev
    Next
    INDEX
    Explanations

    if you mean

    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
    åı¯åIJ¦
    -0.06
     zwar
    -0.06
    ?
    -0.06
    æĸij
    -0.06
    æĪIJåĬŁåIJİ
    -0.06
    idges
    -0.06
     –
    -0.06
    ´
    -0.06
    å¹²åĺĽ
    -0.05
    erbe
    -0.05
    POSITIVE LOGITS
    owi
    0.08
    åĽłæѤèĢĮ
    0.08
    akaan
    0.08
     ìŀĪëĭ¤ë©´
    0.08
    arp
    0.08
    ventura
    0.08
    rex
    0.08
    ëĿ¼ë©´
    0.08
    }elseif
    0.08
    ä»ħä»ħæĺ¯
    0.07
    Activations Density 0.053%

    No Known Activations