© 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. 29260
    Prev
    Next
    INDEX
    Explanations

    would be

    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
    大å°ıå§IJ
    -0.09
    اÙħØ©
    -0.08
    ìłĢ
    -0.07
    acie
    -0.07
    격
    -0.07
    Thrown
    -0.07
    åįĵ
    -0.07
    leb
    -0.07
    æ¯Ķè¾ĥå¤įæĿĤ
    -0.07
    åĵªæľī
    -0.07
    POSITIVE LOGITS
     réfé
    0.06
     Booker
    0.06
    ä¸ĩ件
    0.06
    ollen
    0.06
    rij
    0.06
    ifah
    0.06
     wÅĤaÅĽnie
    0.06
     v
    0.06
    æľĽ
    0.06
    çŁ¥åħ¶
    0.06
    Activations Density 0.183%

    No Known Activations