© 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. 17969
    Prev
    Next
    INDEX
    Explanations

    concluding culmination finally lastly

    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
     initial
    -0.09
    åĪĿå§ĭ
    -0.08
     Initial
    -0.08
    Initial
    -0.08
     inicial
    -0.08
    (initial
    -0.08
     اÙĪÙĦÛĮÙĩ
    -0.07
    initial
    -0.07
    _initial
    -0.07
    æľĢåĪĿçļĦ
    -0.07
    POSITIVE LOGITS
    æľĢåIJİä¸Ģ个
    0.08
    çļĦæľĢåIJİ
    0.08
    æľĢå¾Į
    0.08
     concluding
    0.08
    æľĢåIJİçļĦ
    0.08
    æľĢåIJİ
    0.08
    æľĢåIJİä¸Ģ
    0.07
     culmination
    0.07
    finally
    0.07
     Lastly
    0.07
    Activations Density 0.225%

    No Known Activations