© 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. 22325
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Not in Any Lists

    No Comments

    Negative Logits
    ind
    -0.07
    riend
    -0.06
    orig
    -0.06
    __(
    -0.06
    ora
    -0.06
    aren
    -0.06
    oral
    -0.06
    ç²±
    -0.06
    åĪļåĪļ
    -0.06
    just
    -0.05
    POSITIVE LOGITS
    rv
    0.06
     firm
    0.05
    æĴ°ç¨¿
    0.05
    uki
    0.05
    æķ¢
    0.05
    firm
    0.05
     me
    0.04
    apol
    0.04
    Fir
    0.04
    ÙĩØ©
    0.04
    Activations Density 0.000%

    No Known Activations