© 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. 19060
    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
    ense
    -0.06
    less
    -0.06
     himself
    -0.05
     else
    -0.05
    estic
    -0.05
    ian
    -0.05
    æŀģ端
    -0.05
    ä¸Ģå¥Ĺ
    -0.05
     Ibid
    -0.04
    ä¸Ĭ身
    -0.04
    POSITIVE LOGITS
    æ¦Ĥ
    0.07
    astas
    0.06
    veis
    0.06
    ambo
    0.06
    ergestellt
    0.06
    çļĦéĺħ读
    0.06
    무를
    0.06
    visto
    0.06
    éļ¾æ±Ĥ
    0.06
    家åħ¬åı¸
    0.06
    Activations Density 0.000%

    No Known Activations