© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20062
    Prev
    Next
    INDEX
    Explanations

    des...fichiers

    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
    er
    -0.08
    eru
    -0.08
    erar
    -0.08
    ting
    -0.07
    icient
    -0.07
    eret
    -0.07
    eram
    -0.07
    deo
    -0.06
    åī¤
    -0.06
    forcer
    -0.06
    POSITIVE LOGITS
    ized
    0.07
    нÑĭй
    0.07
    ع
    0.07
    æł·çļĦ
    0.06
    ÑģÑı
    0.06
    ained
    0.06
    avance
    0.06
    agog
    0.06
    quate
    0.06
    ingly
    0.06
    Activations Density 0.003%

    No Known Activations