© 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. 28340
    Prev
    Next
    INDEX
    Explanations

    proportional to

    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
    theon
    -0.08
    æŃ¤èµ·
    -0.07
    estin
    -0.07
    CompleteListener
    -0.07
    ä¸Ģç«Ļ
    -0.07
    egu
    -0.07
    subjects
    -0.07
    å½»åºķ
    -0.07
    å°
    -0.06
    å¦ĤåĽł
    -0.06
    POSITIVE LOGITS
    ponsible
    0.07
    åĽ½åĨħå¤ĸ
    0.07
    代人
    0.07
    _TIMES
    0.07
    åıĺåĮĸ
    0.06
    à¸Ħุ
    0.06
    opus
    0.06
     proportional
    0.06
    steen
    0.06
    xcb
    0.06
    Activations Density 0.019%

    No Known Activations