© 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. 20611
    Prev
    Next
    INDEX
    Explanations

    section titles or list items

    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
    spflicht
    -0.06
    elj
    -0.05
    isser
    -0.05
    ä¹Łæ²¡æľī
    -0.05
    éĥ¨éŨèģĶåIJĪ
    -0.05
    ä¹Łæ²¡
    -0.05
    åĵij
    -0.05
    enov
    -0.05
    æĺ¥å¤ıç§ĭåĨ¬
    -0.05
    inga
    -0.05
    POSITIVE LOGITS
    ulture
    0.06
    åĪĩæĸŃ
    0.06
    主干
    0.06
    DEX
    0.06
    dessen
    0.05
    w
    0.05
    konfirmasi
    0.05
     sout
    0.05
    reta
    0.05
    æŃ£å¼ıçīĪ
    0.05
    Activations Density 0.006%

    No Known Activations