© 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. 19983
    Prev
    Next
    INDEX
    Explanations

    bubble plots, venn diagrams, graphs, trees

    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
    -doc
    -0.06
    å®ĺç½ij
    -0.06
    åIJİèĢħ
    -0.06
     quint
    -0.05
    ä¹ĭä¸ĢçļĦ
    -0.05
     fallback
    -0.05
    ürg
    -0.05
    atap
    -0.05
    åĨħéĥ¨
    -0.05
    ipi
    -0.05
    POSITIVE LOGITS
    represent
    0.07
     representing
    0.07
     represents
    0.06
     representa
    0.06
     représente
    0.06
     represent
    0.06
    æĿ¥è¡¨ç¤º
    0.06
    åĪĻ表示
    0.06
    代表
    0.06
    ä¸Ń表示
    0.06
    Activations Density 0.024%

    No Known Activations