© 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. 16875
    Prev
    Next
    INDEX
    Explanations

    characterized by

    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
    ational
    -0.07
    iah
    -0.06
    toa
    -0.06
     expl
    -0.06
    osing
    -0.06
    à¸Īริà¸ĩ
    -0.06
    ishment
    -0.05
    kah
    -0.05
    udo
    -0.05
    folk
    -0.05
    POSITIVE LOGITS
    wsze
    0.06
    éĺ¿åĵ¥
    0.06
    trate
    0.06
    اÙĨÙĩ
    0.06
    hic
    0.06
    инима
    0.06
    راÙĥ
    0.06
    æĶ»åħ³
    0.06
    RITE
    0.05
    esse
    0.05
    Activations Density 0.026%

    No Known Activations