© 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. 39220
    Prev
    Next
    INDEX
    Explanations

    complex structures or lists

    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
    å°ıé¢ĺ
    -0.09
    éģįåľ°
    -0.08
    å°±æĺ¯ä»İ
    -0.08
    åĪĿè¯ķ
    -0.08
    ä¹ĭäºİ
    -0.07
    éħĿéħ¿
    -0.07
     subsequ
    -0.07
    ìĶ¨
    -0.07
    afen
    -0.07
    æĬij
    -0.07
    POSITIVE LOGITS
    æľīä¸ī个
    0.10
    åĽĽä¸ª
    0.07
    bable
    0.07
    ä¸ī个
    0.07
     constituency
    0.06
     three
    0.06
    pheric
    0.06
    ç¬¬åĽĽä¸ª
    0.06
    éĻ¤äºĨ
    0.06
    åı³æīĭ
    0.06
    Activations Density 0.002%

    No Known Activations