© 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. 569
    Prev
    Next
    INDEX
    Explanations

    example of

    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
    fus
    -0.08
    atil
    -0.08
    ilan
    -0.07
    indel
    -0.07
    lad
    -0.07
    åij¨ä¸Ģèĩ³
    -0.07
    æĭĽæĥ¹
    -0.07
    ÅĤaw
    -0.07
    ingi
    -0.07
     denun
    -0.07
    POSITIVE LOGITS
     (::
    0.08
    eprom
    0.07
    rase
    0.07
    ground
    0.07
    å§
    0.06
     outgoing
    0.06
    ukai
    0.06
    ä½ľåģĩ
    0.06
    æݨ广
    0.06
    olla
    0.06
    Activations Density 0.164%

    No Known Activations