© 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. 14454
    Prev
    Next
    INDEX
    Explanations

    return or returned

    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
    ä¸ĭä¸ĢæŃ¥
    -0.21
    åĪ¨
    -0.20
    ä¸ĢæŃ¥ä¸ĢæŃ¥
    -0.20
    åīįè¿Ľ
    -0.20
    æĶ¶è´¹æłĩåĩĨ
    -0.18
    ä¸ĢæŃ¥æŃ¥
    -0.18
    讲è¯Ŀ
    -0.18
    ahead
    -0.18
    åĩºæĿ¥äºĨ
    -0.17
    æݨ广
    -0.17
    POSITIVE LOGITS
    è¿Ķ
    0.26
    (Return
    0.26
    (return
    0.26
    纥
    0.22
    wards
    0.21
     RETURN
    0.21
    åĽŀåİ»
    0.20
    åĽŀæĿ¥
    0.20
    rij
    0.19
     Returned
    0.19
    Activations Density 0.030%

    No Known Activations