© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 21236
    Prev
    Next
    INDEX
    Explanations

    driving and car use

    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
    交
    -0.05
     ply
    -0.05
     trib
    -0.05
     fibres
    -0.05
    å²ģ
    -0.05
     fibers
    -0.05
    ÙĪع
    -0.05
    åĩº
    -0.05
    ç²¹
    -0.05
    åħ¬å¹³
    -0.05
    POSITIVE LOGITS
    åħļå·¥å§Ķ
    0.06
    vla
    0.06
    æı®
    0.06
    uite
    0.06
    ãģĶ確èªįãģıãģłãģķãģĦ
    0.06
    ostat
    0.06
    å©¿
    0.06
    ç§ģ
    0.06
    доз
    0.06
    ç§ģ家
    0.06
    Activations Density 0.006%

    No Known Activations