© 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. 47651
    Prev
    Next
    INDEX
    Explanations

    acknowledgement or transition

    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
    vice
    -0.08
    vá
    -0.08
    继èĢĮ
    -0.08
    psc
    -0.08
    ായ
    -0.08
    amber
    -0.08
    æĬ¥åIJįæĿ¡ä»¶
    -0.08
    wine
    -0.07
     ?',
    -0.07
     Boo
    -0.07
    POSITIVE LOGITS
    椿
    0.07
     dead
    0.07
    erek
    0.06
    å©ķ
    0.06
    åĩºåħ¥
    0.06
    å°Ķ夫
    0.06
    æīįæĺİçĻ½
    0.06
     quang
    0.06
    uchi
    0.06
    詹
    0.06
    Activations Density 0.002%

    No Known Activations