© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 16778
    Prev
    Next
    INDEX
    Explanations

    blank followed by words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    èĢħåľ¨
    -0.06
    ailer
    -0.06
    ight
    -0.05
    ÙĪادث
    -0.05
    aller
    -0.05
    argon
    -0.05
    icana
    -0.05
    weisen
    -0.05
    лов
    -0.05
    lang
    -0.05
    POSITIVE LOGITS
    teen
    0.07
    ente
    0.07
     annet
    0.07
    itude
    0.07
    issant
    0.06
    tez
    0.06
    اظ
    0.06
    te
    0.06
     Hins
    0.06
     Ñģобой
    0.06
    Activations Density 0.006%

    No Known Activations