© 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. 22326
    Prev
    Next
    INDEX
    Explanations

    doing things

    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
     again
    -0.06
    onie
    -0.06
    inde
    -0.06
    ÙĦات
    -0.06
    laus
    -0.06
    again
    -0.06
     Again
    -0.05
    inti
    -0.05
     AGAIN
    -0.05
    åIJĮæł·
    -0.05
    POSITIVE LOGITS
     rése
    0.06
    sg
    0.06
    nob
    0.06
    糸
    0.06
    nm
    0.05
    rd
    0.05
     appearances
    0.05
    enia
    0.05
    STOP
    0.05
    gak
    0.05
    Activations Density 0.027%

    No Known Activations