© 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. 62230
    Prev
    Next
    INDEX
    Explanations

    biological and scientific terms

    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
    为æѤ
    -0.08
    avin
    -0.08
    вин
    -0.07
    GetObject
    -0.07
    代ä¹ĭ
    -0.07
    èĸĩèĸĩ
    -0.07
    åħ¬åı¸æľī
    -0.07
     hierzu
    -0.07
    вий
    -0.07
    оÑĢо
    -0.07
    POSITIVE LOGITS
     afin
    0.11
    以示
    0.11
     ÑĩÑĤобÑĭ
    0.10
    以确ä¿Ŀ
    0.10
     nhằm
    0.10
     à¹Ģà¸ŀืà¹Īà¸Ń
    0.09
     Ñīоб
    0.09
     ׼×ĵ×Ļ
    0.08
    以éĺ²æŃ¢
    0.08
    使åħ¶
    0.08
    Activations Density 0.615%

    No Known Activations