© 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. 11821
    Prev
    Next
    INDEX
    Explanations

    Outdoor gear and retail

    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
    碧æ¡Ĥ
    -0.24
    artner
    -0.21
    æ¼ĶæĬĢ
    -0.21
     cells
    -0.20
    tenant
    -0.20
    cells
    -0.20
    CLE
    -0.19
     пеÑĢеÑħод
    -0.19
    ç¾İè²Į
    -0.19
    _cells
    -0.18
    POSITIVE LOGITS
    åĻ¨æĿIJ
    0.31
    çī¦
    0.25
    åĻ¨æ¢°
    0.25
    æ»ijéĽª
    0.25
    æĪ·å¤ĸ
    0.24
     ski
    0.24
     backpack
    0.23
     Outdoor
    0.23
    èĥĮåĮħ
    0.23
     Wilderness
    0.23
    Activations Density 0.041%

    No Known Activations