© 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. 20174
    Prev
    Next
    INDEX
    Explanations

    compiler errors

    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
    æĹłæĦ§
    -0.07
    沫
    -0.07
    iley
    -0.06
    ä¸įæĥĬ
    -0.06
    åľ¨èģĮ
    -0.06
    ibli
    -0.06
    äºĮ线
    -0.06
    ä¸ĭæĿ¥çļĦ
    -0.06
    ãģ¾ãģ¾ãģ§
    -0.06
    ľ
    -0.06
    POSITIVE LOGITS
    ungsver
    0.05
    ãģ£
    0.05
    çµIJå±Ģ
    0.05
    engew
    0.05
    ungen
    0.05
    åŁİå¤ĸ
    0.05
    çĥ«
    0.05
    urret
    0.05
    éķľéĿ¢
    0.05
    æĴ
    0.05
    Activations Density 0.022%

    No Known Activations