© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 11787
    Prev
    Next
    INDEX
    Explanations

    wheels and axles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
    ispers
    -0.24
    æ¼Ĥæµģ
    -0.22
    inating
    -0.22
    æ¼Ĥ
    -0.21
    velope
    -0.20
    ampoo
    -0.19
    诱
    -0.19
    ayers
    -0.19
    chos
    -0.18
    anova
    -0.18
    POSITIVE LOGITS
     wheels
    0.25
     shoes
    0.22
    è½®èĥİ
    0.21
    è½®æµģ
    0.21
    è½®
    0.20
    ä¸Ģæ±½
    0.20
    人åĬĽ
    0.20
     WL
    0.20
    vice
    0.20
    å±¥
    0.20
    Activations Density 0.044%

    No Known Activations