© 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. 33197
    Prev
    Next
    INDEX
    Explanations

    write a

    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
    åIJ§
    -0.09
    æĪijåIJ§
    -0.08
    严æĬĬ
    -0.07
     abbast
    -0.07
    à¹Ħว
    -0.06
     RUR
    -0.06
    çľĭçľĭåIJ§
    -0.06
    Lite
    -0.06
    ili
    -0.06
    .tc
    -0.06
    POSITIVE LOGITS
    attet
    0.07
    åĺ´
    0.07
    害
    0.07
    esters
    0.07
    aptcha
    0.07
    holz
    0.07
     submission
    0.07
    ledged
    0.07
    åĪĢåīij
    0.07
    arry
    0.07
    Activations Density 0.003%

    No Known Activations