© 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. 21821
    Prev
    Next
    INDEX
    Explanations

    new products

    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
    ogen
    -0.06
    สัà¸Ļ
    -0.05
    表达对
    -0.05
     expressing
    -0.05
     gen
    -0.05
    åIJĮ级
    -0.05
     بÙĨت
    -0.05
     different
    -0.05
    iv
    -0.05
    or
    -0.05
    POSITIVE LOGITS
    ära
    0.06
    worth
    0.06
    éĶ¦ä¸Ĭæ·»èĬ±
    0.06
     Dodatk
    0.06
    rish
    0.06
    echt
    0.06
    è¿Ľä¸ĢæŃ¥æ·±åĮĸ
    0.05
     веÑī
    0.05
     suplement
    0.05
    èĥ½åĬĽåıĬ
    0.05
    Activations Density 0.002%

    No Known Activations