© 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. 43856
    Prev
    Next
    INDEX
    Explanations

    what to do next

    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
    chin
    -0.07
    iero
    -0.07
     dy
    -0.06
     gar
    -0.06
    cid
    -0.06
    åıģ
    -0.06
    ×Ļר×Ķ
    -0.06
    cen
    -0.06
    atten
    -0.06
    aby
    -0.06
    POSITIVE LOGITS
    othe
    0.09
    ongs
    0.08
    .âĢ¢
    0.08
    ếm
    0.08
    çĶŁæ´»ä¼ļ
    0.08
    uces
    0.08
    imeo
    0.08
    utow
    0.08
    HAL
    0.07
    wab
    0.07
    Activations Density 0.683%

    No Known Activations