© 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. 49548
    Prev
    Next
    INDEX
    Explanations

    'A:' question format

    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
    esen
    -0.07
    ultat
    -0.07
    ird
    -0.07
    enen
    -0.07
    Ñħа
    -0.06
    _syntax
    -0.06
    esti
    -0.06
    uto
    -0.06
    á»įng
    -0.06
    ä¸Ģæī«
    -0.06
    POSITIVE LOGITS
    á»IJ
    0.08
    %A
    0.08
    cies
    0.07
    éĶĢåĶ®çļĦ
    0.07
    itized
    0.07
    wok
    0.07
     Blackburn
    0.07
    讼
    0.07
     ÄijỼi
    0.07
    nhof
    0.07
    Activations Density 0.004%

    No Known Activations