© 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. 20446
    Prev
    Next
    INDEX
    Explanations

    development and testing

    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
    æĦıå¤ĸ
    -0.05
     rec
    -0.05
    ä¸įæľį
    -0.05
    çݰ身
    -0.05
    缴æİ¥æĪĸ
    -0.05
     recip
    -0.05
    éĹ´æİ¥
    -0.04
    缴æİ¥æĪĸéĹ´æİ¥
    -0.04
    elay
    -0.04
     processed
    -0.04
    POSITIVE LOGITS
    æŁ¥çľĭæīĢæľī
    0.07
    clud
    0.07
     sak
    0.06
    ìĤ¬íķŃ
    0.06
    лад
    0.06
    ake
    0.06
    æ®ĥ
    0.06
     вÑĭпа
    0.06
    ÑĥÑī
    0.06
    ske
    0.06
    Activations Density 0.103%

    No Known Activations