© 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. 19939
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    irian
    -0.07
    çłĶ究é¢ĨåŁŁ
    -0.07
    tait
    -0.06
    à¸Ńำ
    -0.06
    uncan
    -0.06
    integrazione
    -0.06
    erties
    -0.06
    +</
    -0.06
    wand
    -0.06
    æĶĿ影師
    -0.06
    POSITIVE LOGITS
    erv
    0.06
    æľīéĻIJ
    0.05
    lo
    0.05
    å¨ĺ
    0.05
    ant
    0.05
    ä»ķ
    0.05
    er
    0.05
    iz
    0.05
    延æŶ
    0.05
    ัà¹īà¸ĩ
    0.05
    Activations Density 0.000%

    No Known Activations