© 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. 18898
    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
    amber
    -0.05
    иÑĢ
    -0.05
    è¦ģèµ°
    -0.05
    Isl
    -0.05
    ute
    -0.05
    insen
    -0.05
    ventajas
    -0.05
    andi
    -0.05
    asi
    -0.05
    å¿ľ
    -0.05
    POSITIVE LOGITS
    æĭĤ
    0.06
    ÑĥÑİÑī
    0.06
     ÙĪاÙĦÙħست
    0.05
    гина
    0.05
     Ryder
    0.05
    ered
    0.05
    使çĶ¨æŶ
    0.05
    boh
    0.05
    å¦Ĥæľī
    0.05
    ìŀħ
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.