© 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. 21188
    Prev
    Next
    INDEX
    Explanations

    components

    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
    alom
    -0.06
    ждÑĥÑİ
    -0.06
    itude
    -0.06
    itation
    -0.06
    s
    -0.06
    обÑī
    -0.06
    acson
    -0.06
    Few
    -0.06
    goog
    -0.06
    fication
    -0.06
    POSITIVE LOGITS
    ê»ı
    0.07
    ×Ļ
    0.07
    illet
    0.07
    ages
    0.06
    yled
    0.06
    bidden
    0.06
    baarheid
    0.06
    AMED
    0.06
    minent
    0.06
    ement
    0.06
    Activations Density 0.032%

    No Known Activations