© 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. 41285
    Prev
    Next
    INDEX
    Explanations

    perhaps, possibly, maybe, likely

    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
    lator
    -0.09
    oris
    -0.09
    iona
    -0.08
    ertif
    -0.08
    å®ŀå¤Ħ
    -0.08
     Ú©ÙĨار
    -0.08
    stät
    -0.08
    razier
    -0.08
    ÑĪÑĤ
    -0.08
    ichtigkeit
    -0.08
    POSITIVE LOGITS
    ä½łçľŁ
    0.08
     possibly
    0.07
    -
    0.07
    åIJįæĢĿ
    0.07
    ç»Īå°Ĩ
    0.07
    ä¹Łè®¸
    0.06
    Nx
    0.06
     maybe
    0.06
    å°ĨæĿ¥
    0.06
     somebody
    0.06
    Activations Density 0.321%

    No Known Activations