© 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. 17660
    Prev
    Next
    INDEX
    Explanations

    code examples, file paths, or technical terms

    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
    ousel
    -0.07
    à¹Ģà¸ŀลิà¸ĩ
    -0.07
    erry
    -0.07
    epatan
    -0.07
    mers
    -0.06
    plier
    -0.06
    enhagen
    -0.06
    ä»»ä½ķåªĴä½ĵ
    -0.06
    cim
    -0.06
    yaj
    -0.06
    POSITIVE LOGITS
    1
    0.07
    0
    0.06
    2
    0.05
    A
    0.05
    4
    0.05
    ç«ĭä½ĵ
    0.05
    anas
    0.05
    rekt
    0.05
    ab
    0.05
     |
    0.05
    Activations Density 0.001%

    No Known Activations