© 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. 11818
    Prev
    Next
    INDEX
    Explanations

    earth day and dates

    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
    è§ĦèĮĥåĮĸ
    -0.20
     paternal
    -0.19
    è§Ħç«ł
    -0.18
     cricket
    -0.18
    olated
    -0.18
    éķij
    -0.17
    éĺ²æ±Ľ
    -0.17
     foc
    -0.17
    pond
    -0.17
    ÑģÑĭл
    -0.17
    POSITIVE LOGITS
    Ľå»º
    0.20
    æ¸ħæī«
    0.19
    vier
    0.19
    工夫
    0.19
    ä¸ĵåĮº
    0.18
    æĹ¶è¡¨ç¤º
    0.18
    åĢ¡è®®
    0.18
    åľĪ
    0.18
    unto
    0.17
    éķ¿å¤§
    0.17
    Activations Density 0.001%

    No Known Activations