© 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. 23938
    Prev
    Next
    INDEX
    Explanations

    recurrences, partition, style, acidosis, resorption

    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
    ndo
    -0.08
    EMAT
    -0.07
    éĢĬ
    -0.07
    }}}
    -0.07
    æĹ¥æľĪ
    -0.07
    é¦Ħ
    -0.07
    ÙĦÙĬÙĦØ©
    -0.07
    éĥ½åIJĪ
    -0.07
    ä¸įè¿ĩä»ĸ
    -0.07
    iono
    -0.07
    POSITIVE LOGITS
    åıįä¹ĭ
    0.11
     vice
    0.10
    缸åºĶçļĦ
    0.10
    ä¸İä¹ĭ
    0.10
    éļıä¹ĭ
    0.10
     convers
    0.09
    缸åºĶ
    0.09
    çĽ¸å¯¹åºĶ
    0.09
    缸æĩī
    0.09
    ä¹Łéļıä¹ĭ
    0.09
    Activations Density 0.284%

    No Known Activations