© 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. 19369
    Prev
    Next
    INDEX
    Explanations

    list.add

    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
    iche
    -0.06
    好åIJ¬
    -0.05
    <<
    -0.05
    edom
    -0.05
     ÑĤак
    -0.05
    меÑģÑĤ
    -0.05
    icast
    -0.05
    ·
    -0.05
    æĸ¹çķ¥
    -0.04
    ÑģÑİ
    -0.04
    POSITIVE LOGITS
    :null
    0.06
    ä¸Ńèĥ½
    0.06
    çĶ·çļĦ
    0.06
    åIJİæĦŁ
    0.06
    áno
    0.06
    enf
    0.06
    山人
    0.06
    uell
    0.06
    urb
    0.05
    een
    0.05
    Activations Density 0.001%

    No Known Activations