© 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. 19180
    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
    er
    -0.08
    ha
    -0.06
    ÑģÑı
    -0.06
    Ùĩ
    -0.06
    è§ģ
    -0.06
    ten
    -0.05
    ×ķ
    -0.05
    ر
    -0.05
    ahn
    -0.05
    ÑĤ
    -0.05
    POSITIVE LOGITS
    åħ¼æĢ»ç»ıçIJĨ
    0.07
     ÙĨاÙģ
    0.06
    cripts
    0.06
    ighth
    0.06
    ork
    0.06
    INU
    0.06
    iations
    0.06
    åĪ°çĽ®åīį
    0.05
    ä»»ä½ķ人
    0.05
    utam
    0.05
    Activations Density 0.000%

    No Known Activations