© 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. 21637
    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
    å¤ĩå¿ĺ
    -0.06
    r
    -0.06
    åīĤçŃī
    -0.06
    SL
    -0.06
    éĶ®
    -0.06
     bois
    -0.05
    aison
    -0.05
    holen
    -0.05
    -Isl
    -0.05
     haired
    -0.05
    POSITIVE LOGITS
    onet
    0.06
    erra
    0.05
    جر
    0.05
    iet
    0.05
     multis
    0.05
    æķ´é«Ķ
    0.05
    ä¹Ī
    0.05
    niv
    0.05
    acks
    0.05
    iec
    0.05
    Activations Density 0.000%

    No Known Activations