© 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. 16774
    Prev
    Next
    INDEX
    Explanations

    third republic

    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
    ä½į
    -0.07
    zat
    -0.07
    1
    -0.06
    -0.06
    ay
    -0.06
     unlike
    -0.06
    a
    -0.06
    E
    -0.06
    æºIJ
    -0.05
    åĽ´
    -0.05
    POSITIVE LOGITS
    Õ®
    0.09
    ä¸įä»ħè¦ģ
    0.08
    _BOTH
    0.08
    adop
    0.08
    ueb
    0.08
    Dame
    0.08
    %D
    0.08
    åħĭåĪ©
    0.07
    xico
    0.07
    ublin
    0.07
    Activations Density 0.075%

    No Known Activations