© 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. 17119
    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
    SEC
    -0.06
     nguyá»ĩt
    -0.05
    hart
    -0.05
    ynet
    -0.05
    esp
    -0.05
    帶æľī
    -0.05
    ID
    -0.05
    à¹Ħม
    -0.05
    ä¸įæĺ¯ä½ł
    -0.05
    空æ°Ķä¸ŃçļĦ
    -0.05
    POSITIVE LOGITS
    éĶ¦æ¶Ľ
    0.07
    lint
    0.06
     practiced
    0.06
    igte
    0.06
    lden
    0.06
    模æĭŁ
    0.06
    éĤ£æŶ
    0.06
    loff
    0.06
    éĤ£æ®µ
    0.06
    襲
    0.05
    Activations Density 0.000%

    No Known Activations