© 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. 16655
    Prev
    Next
    INDEX
    Explanations

    Chinese characters, encoding, February

    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
     y
    -0.05
     Y
    -0.05
    urious
    -0.05
     co
    -0.05
    é¬
    -0.05
    çī¹
    -0.05
    igne
    -0.05
    严
    -0.05
    Y
    -0.05
    头
    -0.05
    POSITIVE LOGITS
    **–
    0.07
    неÑĤо
    0.06
    .assertj
    0.06
    licht
    0.06
    ÑģÑĤеÑĢе
    0.06
    áºŃm
    0.06
     directo
    0.06
    engi
    0.06
     <+
    0.06
     -:
    0.06
    Activations Density 0.001%

    No Known Activations