© 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. 18644
    Prev
    Next
    INDEX
    Explanations

    mathematical simplification

    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
    lon
    -0.06
    allah
    -0.06
    اث
    -0.06
    ÑĢаÑĩи
    -0.05
    θÏħν
    -0.05
     pru
    -0.05
    anza
    -0.05
    æĪIJæīį
    -0.05
     genie
    -0.05
    borne
    -0.05
    POSITIVE LOGITS
    订åĪ¶
    0.06
    æĥ¯
    0.06
    häng
    0.06
    alance
    0.05
    yro
    0.05
    æĥ¦
    0.05
    ëįĶëĭĪ
    0.05
    ibi
    0.05
    ister
    0.05
    éªĩ
    0.05
    Activations Density 0.002%

    No Known Activations