© 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. 21422
    Prev
    Next
    INDEX
    Explanations

    XML and code structures

    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
    åı¯æĺ¯ä¸Ģ
    -0.06
    .AllArgsConstructor
    -0.06
    ounds
    -0.06
    stwo
    -0.06
    ç»Ī
    -0.06
    缴è§Ĥ
    -0.05
    ogu
    -0.05
     laku
    -0.05
    torie
    -0.05
    éĢ²å±ķ
    -0.05
    POSITIVE LOGITS
    æı´
    0.05
    ým
    0.05
    araan
    0.05
    менной
    0.05
    umi
    0.05
     desem
    0.05
    缮çļĦæĺ¯ä¸ºäºĨ
    0.05
    ç²¾ç¥ŀ
    0.05
    ÑģÑĬ
    0.05
    terra
    0.05
    Activations Density 0.001%

    No Known Activations