© 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. 20350
    Prev
    Next
    INDEX
    Explanations

    prices from X to Y

    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
    iqu
    -0.05
    æĻĥ
    -0.05
     enrol
    -0.05
    кÑĢема
    -0.05
    çŁĽçĽ¾çļĦ
    -0.05
    orer
    -0.05
    ä¹ĭåĪĹ
    -0.05
    egram
    -0.05
    åĴĮ客æĪ·
    -0.05
     sometime
    -0.05
    POSITIVE LOGITS
    irsch
    0.06
     zugesch
    0.06
    alang
    0.06
    elen
    0.06
    åħµåĽ¢
    0.05
     SchlieÃŁlich
    0.05
    pin
    0.05
    portun
    0.05
    qing
    0.05
    å©·
    0.05
    Activations Density 0.034%

    No Known Activations