© 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. 17808
    Prev
    Next
    INDEX
    Explanations

    comparisons and outcomes

    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
    pat
    -0.06
    af
    -0.06
    ì§Ģë§Į
    -0.06
    åħ«ä¹Ŀ
    -0.06
    ,but
    -0.06
    av
    -0.06
    ức
    -0.05
    opat
    -0.05
     Est
    -0.05
    ourney
    -0.05
    POSITIVE LOGITS
    ä¸Ń西
    0.06
    órica
    0.06
    å¯Ĩ
    0.06
    å½¼
    0.05
    åħĪè¡Į
    0.05
    ç´ł
    0.05
    ä¸įæ¸ħæ¥ļ
    0.05
     certain
    0.05
    à¸ļาà¸ĩ
    0.05
    æķıæĦŁçļĦ
    0.05
    Activations Density 0.036%

    No Known Activations