© 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. 19134
    Prev
    Next
    INDEX
    Explanations

    subjective affects or influences

    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
    æľĽ
    -0.06
    æķ¢
    -0.05
    å®ŀè´¨
    -0.05
    notice
    -0.05
    èĢĮæĹł
    -0.05
    ä¸Ķåħ·æľī
    -0.05
     perennial
    -0.05
    uali
    -0.05
    并æıIJä¾Ľ
    -0.05
    ä»İä¸į
    -0.05
    POSITIVE LOGITS
    jej
    0.06
    ont
    0.06
    ontology
    0.06
    æľīäºĨæĽ´
    0.06
    agues
    0.06
    æĽ´å¿«åľ°
    0.06
    ÑģÑĤеÑģÑĤвенно
    0.06
    onden
    0.06
    è·Łä»ĸ们
    0.06
     Conforme
    0.06
    Activations Density 0.021%

    No Known Activations