© 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. 16642
    Prev
    Next
    INDEX
    Explanations

    logger the

    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
     to
    -0.05
    æ±Ĥ
    -0.05
    ,
    -0.05
     just
    -0.05
     inter
    -0.05
    —
    -0.05
    лен
    -0.05
    .
    -0.05
    ...
    -0.04
    æĹłè¾ľ
    -0.04
    POSITIVE LOGITS
     hÃło
    0.08
     gunmen
    0.07
    onan
    0.07
    guarded
    0.07
    麻麻
    0.07
    ",-
    0.07
    éĿ¢å±Ĥ
    0.07
    peÄį
    0.07
    ÑĤоÑĢ
    0.07
     sÃŃn
    0.07
    Activations Density 0.003%

    No Known Activations