© 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. 49720
    Prev
    Next
    INDEX
    Explanations

    suffix words like -ency, -ally, -icide, -ship, -acking, -ings, -bund

    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¨ĭ度ä¸Ĭ
    -0.07
    代表æĢ§
    -0.06
    ationToken
    -0.06
    -,
    -0.06
    имо
    -0.06
    orme
    -0.06
    åŃĺåľ¨ä¸ĢäºĽ
    -0.06
    zur
    -0.06
    uze
    -0.06
     Matem
    -0.06
    POSITIVE LOGITS
    ãģ¨åij¼ãģ°ãĤĮãĤĭ
    0.08
    à¸Ļัà¹Īà¸Ļà¹Ģà¸Ńà¸ĩ
    0.08
    arges
    0.07
    ä¹Łåı«
    0.07
    å°±è¿Ļä¹Ī
    0.07
    åį³çĶ¨
    0.07
    jek
    0.07
    λÏİ
    0.07
    ä¹Łç§°
    0.07
    vrier
    0.07
    Activations Density 0.024%

    No Known Activations