© 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. 22331
    Prev
    Next
    INDEX
    Explanations

    direct speech citation starts

    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
    Not in Any Lists

    No Comments

    Negative Logits
    दार
    -0.06
    ight
    -0.05
    колÑĮ
    -0.05
    enne
    -0.05
    åĴĮè´¨éĩı
    -0.05
     implic
    -0.05
     spre
    -0.05
    ank
    -0.05
    ç½¢
    -0.05
     acc
    -0.05
    POSITIVE LOGITS
    ëĥIJ
    0.06
     Sti
    0.06
    lem
    0.06
    gd
    0.06
    æ£Ł
    0.05
     Due
    0.05
    гни
    0.05
    éĢļéĢļ
    0.05
    å··åŃIJ
    0.05
    üss
    0.05
    Activations Density 0.026%

    No Known Activations