© 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. 55542
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and code snippets

    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
    æĤį
    -0.07
    ály
    -0.07
    åѦæĬ¥
    -0.07
    饺
    -0.07
    èĥĮ
    -0.07
    sth
    -0.06
    reed
    -0.06
    emberg
    -0.06
    .compat
    -0.06
    ä¸ĩåıĺ
    -0.06
    POSITIVE LOGITS
     szek
    0.07
    æ¡ĪçļĦ
    0.07
    iffe
    0.07
    à¹Ģลà¹ĩà¸ģà¸Ļà¹īà¸Ńย
    0.07
    æIJŃä¸Ĭ
    0.07
    aise
    0.07
    åį¡è·¯
    0.07
    ordin
    0.07
    .ds
    0.07
    çģĮæ°´
    0.07
    Activations Density 0.022%

    No Known Activations