© 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. 22590
    Prev
    Next
    INDEX
    Explanations

    configuration keys

    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
    ordat
    -0.07
     stringWith
    -0.07
    chtet
    -0.07
    acap
    -0.07
    меÑģÑĤи
    -0.07
    家åĸ»
    -0.07
    åħĴ
    -0.06
    низÑĥ
    -0.06
    åĦ¿çļĦ
    -0.06
    uos
    -0.06
    POSITIVE LOGITS
    j
    0.06
    oj
    0.06
    um
    0.05
    oin
    0.05
    am
    0.05
     latter
    0.05
     "
    0.05
    lah
    0.05
    son
    0.05
    0.05
    Activations Density 0.021%

    No Known Activations