© 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. 17452
    Prev
    Next
    INDEX
    Explanations

    mid-development

    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
    æݧèĤ¡éĽĨåĽ¢æľīéĻIJåħ¬åı¸
    -0.07
    beth
    -0.07
    çĶļèĩ³æľī
    -0.07
    ÑĢио
    -0.07
    éĢļè¿ĩåIJİ
    -0.07
    ---</
    -0.07
    âĢ¦]
    -0.07
    estal
    -0.06
    åºĶçĶ¨æĬĢæľ¯
    -0.06
    fsp
    -0.06
    POSITIVE LOGITS
    ohan
    0.05
    æĶ»
    0.05
     collar
    0.05
     N
    0.05
    anka
    0.05
    .aspx
    0.05
     primer
    0.05
    [
    0.05
    auer
    0.05
    æķıæĦŁ
    0.05
    Activations Density 0.054%

    No Known Activations