© 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. 18815
    Prev
    Next
    INDEX
    Explanations

    code structure elements

    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
    ukum
    -0.06
    endalian
    -0.06
    æĬľç¾¤
    -0.06
     oda
    -0.06
    ä¸Ģ级
    -0.06
    lis
    -0.06
    ä¸ī级
    -0.05
    éma
    -0.05
    endiendo
    -0.05
     vali
    -0.05
    POSITIVE LOGITS
     ours
    0.06
    zy
    0.06
    è·Łä½ł
    0.05
    urg
    0.05
    åIJįåŃĹåı«
    0.05
    å¾Ĺåĥı
    0.05
    åı«ä»Ģä¹Ī
    0.05
    «
    0.05
    称为
    0.05
    elle
    0.05
    Activations Density 0.035%

    No Known Activations