© 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. 18564
    Prev
    Next
    INDEX
    Explanations

    Content-Type and Content-Disposition headers

    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
     relev
    -0.05
    ilar
    -0.05
    ouser
    -0.05
    å¦Ĥæ½®
    -0.05
     spot
    -0.05
     sexually
    -0.05
     adjud
    -0.05
     post
    -0.05
     f
    -0.05
    vie
    -0.05
    POSITIVE LOGITS
    uton
    0.07
    emann
    0.06
    NET
    0.06
    饮水
    0.06
     Bair
    0.06
    æĺ¯ä¸ĢåĪĩ
    0.06
    Äħdź
    0.06
     totul
    0.06
    _many
    0.06
    å¦ĥ
    0.06
    Activations Density 0.003%

    No Known Activations