© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 23161
    Prev
    Next
    INDEX
    Explanations

    predominant, common, important, other

    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
    两éĥ¨åĪĨ
    -0.06
    åıĹçIJĨåIJİ
    -0.06
    à¹Ģà¸Ľà¹ĩà¸Ļà¸ģาร
    -0.06
     elapsed
    -0.06
    èĥ¡æĢĿ
    -0.06
     discipline
    -0.06
     premises
    -0.06
    å®Įæķ´
    -0.06
     antibio
    -0.06
     prer
    -0.06
    POSITIVE LOGITS
    常çĶ¨äºİ
    0.10
     commonly
    0.10
     parmi
    0.10
    ç»ı常被
    0.09
    åľ¨ä¼Ĺå¤ļ
    0.09
     widespread
    0.09
    å¹¿æ³ĽçĶ¨äºİ
    0.09
     wymien
    0.09
    常åIJĥ
    0.09
    常被
    0.09
    Activations Density 0.098%

    No Known Activations