© 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. 20263
    Prev
    Next
    INDEX
    Explanations

    at the time

    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
    ing
    -0.06
    деле
    -0.06
    åĪĨä¹ĭä¸Ģ
    -0.06
    åį³éĢĿ
    -0.05
    æĹ¶ä»£çļĦ
    -0.05
     hale
    -0.05
    late
    -0.05
    iš
    -0.05
    æĹ¶ä»£
    -0.05
     vot
    -0.05
    POSITIVE LOGITS
    yla
    0.06
    å¾ĢæľŁç²¾å½©
    0.06
    ixo
    0.06
    ems
    0.06
    allas
    0.06
    cem
    0.06
    imer
    0.06
    heil
    0.06
    æĽ´å¿«çļĦ
    0.06
    oley
    0.05
    Activations Density 0.012%

    No Known Activations