© 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. 17667
    Prev
    Next
    INDEX
    Explanations

    signal generation and transmission

    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
    åİĭå²ģéĴ±
    -0.06
    erts
    -0.06
    ervas
    -0.06
    å®ŀæķĪæĢ§
    -0.06
    dens
    -0.06
    .authorization
    -0.06
    æĿĥå¨ģæĢ§
    -0.06
    åĪ°åĵªéĩĮ
    -0.05
    æĺĬ天
    -0.05
     fas
    -0.05
    POSITIVE LOGITS
    åĴĮå¤ĦçIJĨ
    0.08
    processing
    0.06
    èģĶ
    0.06
     processing
    0.06
    comp
    0.06
     اÙĦخاÙħ
    0.06
    åıĬæŶå¤ĦçIJĨ
    0.06
    è¯ī
    0.05
    océ
    0.05
     processed
    0.05
    Activations Density 0.121%

    No Known Activations