© 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. 11054
    Prev
    Next
    INDEX
    Explanations

    direction or directions

    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
    ç°Į
    -0.22
     brom
    -0.20
    -filled
    -0.19
     Cleaner
    -0.19
     Picks
    -0.19
    OND
    -0.19
    idy
    -0.19
    æ³ħ
    -0.18
     bump
    -0.18
     uncont
    -0.18
    POSITIVE LOGITS
    æĸ¹åIJij
    0.31
    direction
    0.29
     directions
    0.27
     напÑĢав
    0.25
     Directions
    0.25
    Directions
    0.25
    .direction
    0.24
     direction
    0.24
    åįĹ
    0.24
    çļĦæĸ¹åIJij
    0.23
    Activations Density 0.017%

    No Known Activations