© 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. 18404
    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
    êt
    -0.08
    ôt
    -0.07
    egah
    -0.07
    pha
    -0.07
     Vô
    -0.06
    ignan
    -0.06
    utate
    -0.06
     mengusung
    -0.06
    cox
    -0.06
    åĽłäºº
    -0.06
    POSITIVE LOGITS
     -
    0.05
    ir
    0.05
    æĺ¯çĶ¨
    0.05
     trop
    0.05
    or
    0.05
    inde
    0.05
    åºĶ该
    0.05
    z
    0.05
     spread
    0.05
    n
    0.05
    Activations Density 0.000%

    No Known Activations