© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1459
    Prev
    Next
    INDEX
    Explanations

    holiday season

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
     assignable
    -0.27
    éĤ£ä¸Ģ天
    -0.26
    å®Įæķ´
    -0.26
    墨
    -0.25
    è¿Ļä¸Ģ天
    -0.24
    缴å±ŀ
    -0.24
     scoped
    -0.24
    大ä¼ļ
    -0.24
    ĶĦ
    -0.24
    å®Įæķ´çļĦ
    -0.23
    POSITIVE LOGITS
    çļĦæ°Ķæģ¯
    0.25
    дÑĥ
    0.24
    stoff
    0.24
    æ°Ķæģ¯
    0.24
    spir
    0.23
    rong
    0.23
    chts
    0.22
    OMP
    0.21
    rk
    0.21
    æµĵæµĵ
    0.21
    Activations Density 0.015%

    No Known Activations