© 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. 58094
    Prev
    Next
    INDEX
    Explanations

    kinetics and analysis

    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
     Pró
    -0.08
    -dismiss
    -0.07
     excursion
    -0.07
    íħį
    -0.07
    +xml
    -0.07
    chetto
    -0.07
    باÙĩ
    -0.07
    <footer
    -0.07
    èī¯åĵģ
    -0.07
     ÐĿедоÑģÑĤа
    -0.07
    POSITIVE LOGITS
    Variables
    0.09
    allis
    0.09
     coefficients
    0.09
     variables
    0.08
    äºĮ级
    0.08
    .variables
    0.07
     Variables
    0.07
    empel
    0.07
     derived
    0.07
    trin
    0.07
    Activations Density 0.003%

    No Known Activations