© 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. 18419
    Prev
    Next
    INDEX
    Explanations

    reading input from code

    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
    vert
    -0.06
    anne
    -0.06
    åľ°å¸¦
    -0.05
    ed
    -0.05
     accessible
    -0.05
    åĴª
    -0.05
    idou
    -0.05
    度
    -0.05
    e
    -0.05
    tat
    -0.05
    POSITIVE LOGITS
    æŃ¢
    0.06
    intree
    0.06
    orsch
    0.06
     configuration
    0.06
     aja
    0.05
    Einst
    0.05
    ffit
    0.05
    rupt
    0.05
    å½ĵä¹ĭ
    0.05
    auer
    0.05
    Activations Density 0.002%

    No Known Activations