© 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. 18147
    Prev
    Next
    INDEX
    Explanations

    pressing against

    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
    วิà¸Ļ
    -0.06
    å¿ĺä¸įäºĨ
    -0.06
    ÑīинÑĭ
    -0.05
    мок
    -0.05
    onders
    -0.05
    Stick
    -0.05
    اپ
    -0.05
    åı¯åĸľ
    -0.05
     missed
    -0.05
    è®°å½ķçļĦ
    -0.05
    POSITIVE LOGITS
    oad
    0.06
    åİĭè¿«
    0.06
    iben
    0.06
     dr
    0.05
     Beschwerden
    0.05
    çļĦ交éĢļ
    0.05
     obstruction
    0.05
    ä¸į让
    0.05
    马æĸ¯
    0.05
     headaches
    0.05
    Activations Density 0.178%

    No Known Activations