© 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. 22284
    Prev
    Next
    INDEX
    Explanations

    off of

    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
    ly
    -0.10
    dür
    -0.07
    ously
    -0.07
    ized
    -0.07
    deo
    -0.06
    ous
    -0.06
    izing
    -0.06
    IZE
    -0.06
    osity
    -0.06
    ë¡ľ
    -0.06
    POSITIVE LOGITS
    ivity
    0.07
    ÑģÑİда
    0.07
    ensively
    0.06
    ihad
    0.06
    iveness
    0.06
    ãģĵãģ¡ãĤīãģ¯
    0.06
    tures
    0.06
     Ðļаза
    0.06
    صاÙĦ
    0.06
    iculty
    0.06
    Activations Density 0.030%

    No Known Activations