© 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. 21753
    Prev
    Next
    INDEX
    Explanations

    programming output statements

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    éŁ¿
    -0.06
    åĵį
    -0.05
    ogo
    -0.05
    æ¤Ĵ
    -0.05
    ç®±
    -0.05
    ább
    -0.05
    æIJĶ
    -0.05
    é«ĺç²¾
    -0.05
    åij½åIJį
    -0.05
    ako
    -0.05
    POSITIVE LOGITS
    çŁ¥çļĦ
    0.06
    osit
    0.06
    è·ijè·¯
    0.06
    muz
    0.06
    еÑĢж
    0.05
    è¯Ŀ说
    0.05
    uan
    0.05
    约å®ļçļĦ
    0.05
    说好
    0.05
    reven
    0.05
    Activations Density 0.001%

    No Known Activations