© 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. 17891
    Prev
    Next
    INDEX
    Explanations

    se followed by verb

    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
    ation
    -0.09
    ع
    -0.07
    shire
    -0.07
    actic
    -0.07
    recht
    -0.07
    aménagement
    -0.07
    ting
    -0.06
    าà¸Ĭาà¸ķิ
    -0.06
    éĻ¢éķ¿
    -0.06
    δÏģο
    -0.06
    POSITIVE LOGITS
    ؤÙĦاء
    0.09
    s
    0.07
    ä½Ĩä¸įéĻIJäºİ
    0.07
    à¸Ńีà¹ī
    0.07
    poÅĽred
    0.07
    ί
    0.06
    era
    0.06
    конÑģÑĥлÑĮÑĤи
    0.06
    eing
    0.06
    sider
    0.06
    Activations Density 0.012%

    No Known Activations