© 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. 38671
    Prev
    Next
    INDEX
    Explanations

    section markers and non-latin scripts

    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
    æľīä¸ĭåĪĹ
    -0.08
    çļĦä»»ä½ķ
    -0.08
    rages
    -0.08
    estal
    -0.08
    åIJĦç§įéĹ®é¢ĺ
    -0.08
    rire
    -0.07
    orz
    -0.07
    erness
    -0.07
     ibunya
    -0.07
    rowse
    -0.07
    POSITIVE LOGITS
    å®ħ
    0.07
    æŃ£æĸĩ
    0.07
     capitalized
    0.06
    为人æ°ijæľįåĬ¡
    0.06
    ç®Ģè¿°
    0.06
    ä¸Ģè¨Ģ
    0.06
    à¹Ģà¸Ķà¸Ĭ
    0.06
    èĤ¥çļĤ
    0.06
    adata
    0.06
     oci
    0.06
    Activations Density 0.070%

    No Known Activations