© 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. 19781
    Prev
    Next
    INDEX
    Explanations

    los and following words

    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
    venue
    -0.08
    nde
    -0.07
    er
    -0.07
    tecnolog
    -0.07
    ure
    -0.07
    äººæł¼
    -0.07
    ìĸ´
    -0.06
    ìĪĺ
    -0.06
    ÑģÑĤÑĮ
    -0.06
    деÑģÑıÑĤ
    -0.06
    POSITIVE LOGITS
    ات
    0.08
    s
    0.08
     demás
    0.07
    dır
    0.07
    edere
    0.07
    ska
    0.07
    ä¼ĹæīĢåij¨çŁ¥
    0.07
    è´¨çļĦ
    0.06
    اتÙĩا
    0.06
    omething
    0.06
    Activations Density 0.005%

    No Known Activations