© 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. 20683
    Prev
    Next
    INDEX
    Explanations

    common, public, question words

    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
     almost
    -0.06
    åĩłä¹İ
    -0.05
     Almost
    -0.05
    jerne
    -0.05
     most
    -0.05
    ç¡®
    -0.05
    èĭ¥æľī
    -0.05
     Fe
    -0.05
    çļĦåŁºæľ¬
    -0.05
    ç¡®æľī
    -0.05
    POSITIVE LOGITS
    onical
    0.06
    ÙĥÙĬÙĨ
    0.06
    éc
    0.06
    odr
    0.06
    à§įষ
    0.06
    veen
    0.06
    æ¦Ľ
    0.05
    ÑģÑģ
    0.05
    æ³Ľ
    0.05
    çĶ°
    0.05
    Activations Density 0.037%

    No Known Activations