© 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. 19196
    Prev
    Next
    INDEX
    Explanations

    Semi-Structured

    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
    orge
    -0.06
    åħļæĢ»æĶ¯ä¹¦è®°
    -0.06
    iero
    -0.06
    towe
    -0.06
    igel
    -0.06
    gett
    -0.06
    Ú¾ÛĴ
    -0.06
    atorio
    -0.06
    ynie
    -0.06
    eby
    -0.06
    POSITIVE LOGITS
    pl
    0.06
    顾
    0.05
     Bernstein
    0.05
    ak
    0.05
    rz
    0.05
    olon
    0.05
     AR
    0.05
    AR
    0.05
    verse
    0.04
     AB
    0.04
    Activations Density 0.258%

    No Known Activations