© 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. 17575
    Prev
    Next
    INDEX
    Explanations

    import statements

    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
    游走
    -0.07
    eel
    -0.07
    szer
    -0.07
    URNS
    -0.06
    agio
    -0.06
    gerecht
    -0.06
     طاÙĦ
    -0.06
    unca
    -0.06
    QUE
    -0.06
    impat
    -0.06
    POSITIVE LOGITS
     (
    0.06
    essian
    0.05
     to
    0.05
    '
    0.05
     M
    0.05
     sd
    0.05
    ivate
    0.05
    land
    0.05
    em
    0.05
     etc
    0.05
    Activations Density 0.013%

    No Known Activations