© 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. 19115
    Prev
    Next
    INDEX
    Explanations

    list and array syntax

    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
    éĻIJåĪ¶æĢ§
    -0.05
    æīĵåľ¨
    -0.05
    深山
    -0.05
    祥
    -0.05
    á»ķ
    -0.05
    ive
    -0.05
    vt
    -0.05
     بخشÛĮ
    -0.05
    ÉĻlÉĻ
    -0.05
     Wah
    -0.05
    POSITIVE LOGITS
    alach
    0.06
    ä¸Ĭå½ĵ
    0.06
     neum
    0.06
    ønn
    0.06
     \`
    0.06
     inal
    0.06
    Ñģле
    0.06
     Fool
    0.06
    ROP
    0.05
     Terp
    0.05
    Activations Density 0.021%

    No Known Activations