© 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. 20768
    Prev
    Next
    INDEX
    Explanations

    groups affected by actions

    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
    软硬
    -0.06
    ä¸ĢåĽŀäºĭ
    -0.06
    Ä©nh
    -0.06
    ãģ¡
    -0.06
    üll
    -0.06
    ׾×IJ
    -0.05
    å¤ĸå±Ĥ
    -0.05
    population
    -0.05
    _population
    -0.05
    æĢ
    -0.05
    POSITIVE LOGITS
     sharing
    0.07
    usz
    0.06
     inconven
    0.06
    repid
    0.06
    ivor
    0.06
    sharing
    0.06
    åħļç»ĦæĪIJåijĺ
    0.06
     gerecht
    0.05
    è®©æĽ´å¤ļ
    0.05
    oust
    0.05
    Activations Density 0.029%

    No Known Activations