© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19515
    Prev
    Next
    INDEX
    Explanations

    transmission and gearbox

    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
    å¾ĢéĩĮ
    -0.05
    uer
    -0.05
     deco
    -0.05
    声åĬ¿
    -0.05
     respiratory
    -0.05
    .ins
    -0.05
     Bust
    -0.05
    кÑĥпа
    -0.05
    æıŃ
    -0.05
    lint
    -0.05
    POSITIVE LOGITS
    manual
    0.07
    pas
    0.07
     пеÑĢедаÑĩ
    0.07
    åıĺéĢŁç®±
    0.07
    csi
    0.07
    wheel
    0.07
     fractions
    0.07
    é½Ĵ
    0.07
    voi
    0.07
    Wheel
    0.06
    Activations Density 0.044%

    No Known Activations