© 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. 17633
    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
    è§Ĩ
    -0.06
     concl
    -0.06
    天
    -0.06
    åħ¶ä»ĸ
    -0.06
    “
    -0.06
    éĤ£
    -0.05
    .mo
    -0.05
    éģµå®Ī
    -0.05
    é¾
    -0.05
    ä¹Ł
    -0.05
    POSITIVE LOGITS
    igraph
    0.06
    urias
    0.06
    积æŀģåIJijä¸ĬçļĦ
    0.06
    å°¼å°Ķ
    0.06
    éĿŀ常丰å¯Į
    0.06
    èĩĬ
    0.06
    èĩªä¸Ģä½ĵ
    0.06
     ÑĢек
    0.06
     **(
    0.06
    丰å¯Įå¤ļæł·çļĦ
    0.06
    Activations Density 0.000%

    No Known Activations