© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12579
    Prev
    Next
    INDEX
    Explanations

    phases: wind-up, cocking, acceleration, and follow-through.phased actions

    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
    çİ°æľīçļĦ
    -0.21
    æĭ´
    -0.20
    第äºĮç§į
    -0.20
    åı¦ä¸Ģç§į
    -0.20
    åĬ³åĬ¡
    -0.19
    çİ°æľī
    -0.19
    ä¼ĺç§ĢçļĦ
    -0.19
    æ¡Ĩ
    -0.19
     Bryan
    -0.19
    cep
    -0.18
    POSITIVE LOGITS
     afterwards
    0.27
    éļıä¹ĭ
    0.26
     afterward
    0.24
     thereafter
    0.24
    éĺ¶æ®µ
    0.23
     заÑĤем
    0.23
    оÑĢÑĤ
    0.20
    ä¹ĭåIJİ
    0.20
     Afterwards
    0.20
    åĨįåĪ°
    0.20
    Activations Density 0.238%

    No Known Activations