© 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. 2462
    Prev
    Next
    INDEX
    Explanations

    partner, largest, extradition, bilateral

    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
    åIJĦç»Ħ
    -0.08
    åİŁå§ĭçļĦ
    -0.08
    oden
    -0.08
    usak
    -0.08
    大人们
    -0.07
    ugt
    -0.07
    ycz
    -0.07
    ÑĢони
    -0.07
     dads
    -0.07
    çĪ¸çĪ¸å¦Īå¦Ī
    -0.07
    POSITIVE LOGITS
     fellow
    0.11
    æĺ¯ä¸İ
    0.10
    以åıĬä¸İ
    0.10
    对éĿ¢
    0.09
    åĪĹ
    0.09
    ä¸Ńä¸İ
    0.09
    éĢļè¿ĩä¸İ
    0.08
     partner
    0.08
    éĤ»å±ħ
    0.08
     NotImplemented
    0.08
    Activations Density 0.035%

    No Known Activations