© 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. 20057
    Prev
    Next
    INDEX
    Explanations

    where in the page

    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
    en
    -0.05
    çļĦéĢļçŁ¥
    -0.05
    aly
    -0.05
    ализ
    -0.05
    izia
    -0.05
    å¦ĤæĦı
    -0.05
     chá»īnh
    -0.05
     mandatory
    -0.05
    ä¸įçķı
    -0.05
     pember
    -0.05
    POSITIVE LOGITS
    icole
    0.07
    ä¸Ī
    0.06
    åĨĴ
    0.06
    åIJŀåIJIJ
    0.06
    ä¸įæį¢
    0.06
     Commiss
    0.06
    specs
    0.06
    ROTO
    0.06
    åIJĪçī©
    0.06
    adini
    0.06
    Activations Density 0.001%

    No Known Activations