© 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. 18306
    Prev
    Next
    INDEX
    Explanations

    http, licensed, copyright, date, page

    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
    s
    -0.09
    äºĨ
    -0.08
    ات
    -0.07
    Ñĭ
    -0.07
    ä½Ĩä¸įéĻIJäºİ
    -0.07
    аÑģÑĮ
    -0.06
    sene
    -0.06
    ت
    -0.06
    ãģĦãĤĭ
    -0.06
    quiera
    -0.06
    POSITIVE LOGITS
    o
    0.09
    ponent
    0.08
    a
    0.08
    othe
    0.08
    erio
    0.08
    er
    0.07
    ا
    0.07
    konfirmasi
    0.07
    ly
    0.07
    erot
    0.07
    Activations Density 0.028%

    No Known Activations