© 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. 18991
    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
    æ»ĭ
    -0.06
    åªĴ
    -0.06
    åºľ
    -0.06
    åĬ©
    -0.06
    egram
    -0.06
    缸åħ³æݨèįIJ
    -0.05
    ä¸įåŃĺåľ¨
    -0.05
    inst
    -0.05
    ä¸įè¡Į
    -0.05
    verständnis
    -0.05
    POSITIVE LOGITS
    zar
    0.06
    добÑĢо
    0.05
    éĻįåĪ°
    0.05
    нÑĮ
    0.05
    γÏī
    0.05
    磫
    0.05
    ci
    0.05
    è®°å½ķä¸ĭ
    0.05
    è®°å½ķäºĨ
    0.05
    Kalau
    0.05
    Activations Density 0.000%

    No Known Activations