© 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. 48107
    Prev
    Next
    INDEX
    Explanations

    time stamps and dates

    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
    ç»´
    -0.06
    ifer
    -0.06
    è§ģçļĦ
    -0.06
    atile
    -0.06
    azo
    -0.06
    ink
    -0.06
    å¿Ĺ
    -0.05
    ç¶Ń
    -0.05
    åĩĿ
    -0.05
    pecially
    -0.05
    POSITIVE LOGITS
    ftime
    0.09
    è§Ĩ
    0.08
    oyal
    0.08
    oola
    0.08
    MAIL
    0.08
     chôm
    0.08
    oyer
    0.07
    -License
    0.07
    dbg
    0.07
    oland
    0.07
    Activations Density 0.001%

    No Known Activations