© 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. 18784
    Prev
    Next
    INDEX
    Explanations

    **punctuation followed by sentence continuation**

    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
    adam
    -0.06
    enn
    -0.06
     subtly
    -0.06
     brit
    -0.06
    ockey
    -0.06
    åĿļæĮģ
    -0.06
     اÙĦÙħÙĨØ´
    -0.05
     ÐŁÑĢедлага
    -0.05
    ðŁĺī
    -0.05
     exploits
    -0.05
    POSITIVE LOGITS
    éªĤ
    0.06
    erei
    0.06
    defs
    0.06
    ä¿¡
    0.05
    Switch
    0.05
    çĭĤ
    0.05
     lầm
    0.05
    ä¸Ń央
    0.05
    åı¦ä¸Ģæĸ¹éĿ¢
    0.05
    apphire
    0.05
    Activations Density 0.012%

    No Known Activations