© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 52076
    Prev
    Next
    INDEX
    Explanations

    _data or _id followed by quotes

    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
    Negative Logits
     latter
    -0.08
    åıĸèĢĮ代ä¹ĭ
    -0.07
     thereof
    -0.07
    ^K
    -0.07
    ä¹Łèĥ½å¤Ł
    -0.07
     Neto
    -0.07
    åĽºéĨĩ
    -0.07
    éĥ½èĥ½å¤Ł
    -0.06
     längst
    -0.06
    åĬłæĭ¿å¤§
    -0.06
    POSITIVE LOGITS
    ule
    0.10
     Zaj
    0.07
    rej
    0.07
     Sommer
    0.06
    leb
    0.06
     Sender
    0.06
    bre
    0.06
    ty
    0.06
    andon
    0.06
    letcher
    0.06
    Activations Density 0.448%

    No Known Activations