© 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. 19075
    Prev
    Next
    INDEX
    Explanations

    loading datasets

    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
    str
    -0.05
    彬
    -0.05
    ick
    -0.05
    plast
    -0.05
    è¹
    -0.05
     respect
    -0.05
    æ±°
    -0.05
     inst
    -0.05
    ouch
    -0.05
     aw
    -0.05
    POSITIVE LOGITS
    tones
    0.07
    å¸ĥç½®
    0.06
    廳
    0.06
    vlak
    0.06
    é£ŁçĶ¨
    0.06
     неоÑĤ
    0.06
    utherland
    0.06
    ilton
    0.06
    ä¼¼æĺ¯
    0.06
    è¦ģæīĵ
    0.06
    Activations Density 0.002%

    No Known Activations