© 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. 21700
    Prev
    Next
    INDEX
    Explanations

    contains `r'lan` sequence

    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
    rodu
    -0.07
    产åĵģåĴĮ
    -0.06
    aku
    -0.06
    equals
    -0.06
    еÑģа
    -0.06
    epak
    -0.06
    erede
    -0.05
    azan
    -0.05
    ÏĥμαÏĦα
    -0.05
     ÑĢав
    -0.05
    POSITIVE LOGITS
    ä¹Ŀå¹´
    0.06
    æijĬ
    0.06
    æĶ¤
    0.06
    è½®
    0.06
    輪
    0.06
    éļĶ
    0.06
    Ñģловно
    0.05
    ä¸Ģè¡Į
    0.05
    ãģ°
    0.05
    _COMP
    0.05
    Activations Density 0.003%

    No Known Activations