© 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. 17818
    Prev
    Next
    INDEX
    Explanations

    round

    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
    eceÄŁi
    -0.06
    eceÄŁini
    -0.06
    ä¸įå®Įåħ¨ç»Łè®¡
    -0.06
    дово
    -0.06
    ories
    -0.06
    uer
    -0.06
    пÑĢоÑĤи
    -0.06
    chten
    -0.06
    verkauf
    -0.06
     próprio
    -0.06
    POSITIVE LOGITS
    ommy
    0.07
    britann
    0.06
    wo
    0.06
    agne
    0.06
    بط
    0.06
    (CC
    0.06
    TERN
    0.06
    WSC
    0.06
    ttp
    0.06
    (COM
    0.06
    Activations Density 0.013%

    No Known Activations