© 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. 18437
    Prev
    Next
    INDEX
    Explanations

    book titles and academic topics

    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
    yll
    -0.05
    rod
    -0.05
     followed
    -0.05
    ìĿµ
    -0.05
    edi
    -0.05
    еÑĪ
    -0.05
    eness
    -0.05
    iss
    -0.05
    å°ģéĹŃå¼ı
    -0.05
    ara
    -0.05
    POSITIVE LOGITS
    langen
    0.06
    æĴijçĿĢ
    0.06
    gau
    0.06
    å°±æĺ¯
    0.06
    oseb
    0.05
    æĺ¯åIJĹ
    0.05
    ä¸ĩåĥıç´ł
    0.05
    uly
    0.05
    urit
    0.05
    вани
    0.05
    Activations Density 0.278%

    No Known Activations