© 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. 18756
    Prev
    Next
    INDEX
    Explanations

    still

    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
    人åķĬ
    -0.06
    è¶Ĭåıij
    -0.06
    äºĨä¸Ģæł·
    -0.06
    доÑĢов
    -0.06
    æĦĪåıij
    -0.05
    æ±ĩ
    -0.05
    under
    -0.05
     maintained
    -0.05
    åıĪä¸Ģ
    -0.05
    æĽ´æĸ°çļĦ
    -0.05
    POSITIVE LOGITS
    rÃŃ
    0.06
    rms
    0.06
    ä¸ĢæĻĤ
    0.05
    æŃ
    0.05
    èªĩ
    0.05
    ä¸ĢæŶ
    0.05
    宣读
    0.05
     linger
    0.05
     precautions
    0.05
    طات
    0.05
    Activations Density 0.018%

    No Known Activations