© 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. 12066
    Prev
    Next
    INDEX
    Explanations

    walking and jogging

    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
    enh
    -0.21
     Seats
    -0.21
    ä¸Ģçŀ¬éĹ´
    -0.20
    èĨı
    -0.20
    èł¢
    -0.20
    åºĬä½į
    -0.19
    ç»Ī身
    -0.19
    çĨł
    -0.19
    ewise
    -0.19
    èį¸
    -0.19
    POSITIVE LOGITS
    æķ£æŃ¥
    0.31
    漫æŃ¥
    0.24
    ä¸Ģè¶Ł
    0.24
    å·¡éĢ»
    0.24
    æ¸ħæĻ¨
    0.23
    éĶ»çĤ¼
    0.22
    èµī
    0.22
    éģĽ
    0.21
    æłijæŀĹ
    0.21
    èµ°
    0.21
    Activations Density 0.030%

    No Known Activations