© 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. 638
    Prev
    Next
    INDEX
    Explanations

    plain followed by a noun

    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
    leman
    -0.10
    Ñļи
    -0.09
    ibold
    -0.09
    ×ķ×IJ
    -0.09
    ahui
    -0.09
    ç¿¡
    -0.09
    ibaldi
    -0.08
    å°Ķçī¹
    -0.08
     volna
    -0.08
    spiel
    -0.08
    POSITIVE LOGITS
    ness
    0.09
    /plain
    0.08
    æĺĵæĩĤ
    0.08
    -hearted
    0.07
    flat
    0.07
     text
    0.07
     Hammond
    0.07
    èį¡èį¡
    0.07
    itud
    0.06
    æľ´
    0.06
    Activations Density 0.010%

    No Known Activations