© 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. 14746
    Prev
    Next
    INDEX
    Explanations

    location inquiry

    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
    æľĢ大çļĦ
    -0.25
    æľĢå¤ļçļĦ
    -0.22
    们çļĦ
    -0.20
    ä½ľä¸ºä¸ĢåIJį
    -0.20
    ä¸ºæľŁ
    -0.20
    马æĿ¥
    -0.19
    åĶ¯æľī
    -0.19
    æľĢ主è¦ģçļĦ
    -0.19
    æĬ¤èº«
    -0.18
    å½ĵä¹ĭæĹłæĦ§
    -0.18
    POSITIVE LOGITS
    æİıåĩº
    0.21
    çĿ¦
    0.19
    æīįå¹²
    0.19
    å¤ĸçķĮ
    0.18
    æīį
    0.18
    CurrentValue
    0.18
    >NN
    0.18
    вал
    0.18
    imers
    0.17
    .getMinutes
    0.17
    Activations Density 0.097%

    No Known Activations