© 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. 21597
    Prev
    Next
    INDEX
    Explanations

    explaining actions and processes

    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
     برس
    -0.07
     Bagno
    -0.07
    ç¡
    -0.07
    ambo
    -0.07
    代
    -0.07
    代为
    -0.06
    çª
    -0.06
    æĿ¥
    -0.06
    alis
    -0.06
    à¸ģระ
    -0.06
    POSITIVE LOGITS
    eware
    0.08
    å±ħåīį
    0.07
    icolor
    0.07
    åijĬè¯īä»ĸ们
    0.07
    essed
    0.07
    缴æİ¥æĪĸéĹ´æİ¥
    0.07
    éĺħè¯»æľ¬æĸĩåīį
    0.07
    大家ä¸Ģèµ·
    0.07
    -archive
    0.07
    å¤ĦçIJĨ设å¤ĩ
    0.07
    Activations Density 0.002%

    No Known Activations