© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 18003
    Prev
    Next
    INDEX
    Explanations

    http or https URLs

    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
    ص
    -0.07
     Buckley
    -0.06
    romatic
    -0.06
    лага
    -0.06
    дели
    -0.06
    oints
    -0.06
    atique
    -0.06
    instein
    -0.06
    åĨĮ
    -0.06
     encount
    -0.06
    POSITIVE LOGITS
    ris
    0.05
    åĭī
    0.05
    OPS
    0.05
    åĪ°æĸ°
    0.05
    åĪ°åħ¶ä»ĸ
    0.05
    ame
    0.05
     /
    0.05
    uret
    0.05
    ep
    0.05
    ¿
    0.05
    Activations Density 0.021%

    No Known Activations