© 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. 17507
    Prev
    Next
    INDEX
    Explanations

    connect to external networks

    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
    ÑĩеÑĢед
    -0.06
     tread
    -0.06
    çĩĻ
    -0.06
    çĥ«
    -0.06
     split
    -0.06
    gres
    -0.06
    æŬ
    -0.06
    æĹĹèĪ°åºĹ
    -0.06
     Sat
    -0.05
     اÙĦÙĪÙĦ
    -0.05
    POSITIVE LOGITS
    رة
    0.06
    å¤ĸ
    0.06
    æļ´éľ²åľ¨
    0.05
    æļ´éľ²
    0.05
     Exposure
    0.05
     exposures
    0.05
    atus
    0.05
    éĥ´
    0.05
    å¤ĸçļĦ
    0.05
    ar
    0.05
    Activations Density 0.033%

    No Known Activations