© 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. 18519
    Prev
    Next
    INDEX
    Explanations

    feasibility, possibilities, options

    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
    اÙģÙĦ
    -0.05
    à¸Ľà¸£à¸°à¸Īำ
    -0.05
    ostat
    -0.05
     inverted
    -0.05
     à¸Ľà¸£à¸°à¸Īำ
    -0.05
    åįĩèĩ³
    -0.05
    icu
    -0.05
    rawer
    -0.05
    ldb
    -0.05
    çĶ¨æĿ¥
    -0.05
    POSITIVE LOGITS
    设æĥ³
    0.07
    åı¯è¡ĮæĢ§
    0.07
     feasibility
    0.07
    æĥ³è±¡ä¸ŃçļĦ
    0.07
    åı¯è¡Į
    0.07
    ussion
    0.06
    åı¯è¡ĮçļĦ
    0.06
    -setup
    0.06
    lagen
    0.06
    /setup
    0.06
    Activations Density 0.026%

    No Known Activations