© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51346
    Prev
    Next
    INDEX
    Explanations

    on time in full

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    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
    æļĦ
    -0.10
    nia
    -0.10
    uture
    -0.09
    让åѦçĶŁ
    -0.09
    åŀĦæĸŃ
    -0.08
    åѵåĮĸ
    -0.08
    æİĮæı¡
    -0.08
    Pub
    -0.08
    å¹³åı°
    -0.08
     stir
    -0.08
    POSITIVE LOGITS
    ç²¾çĽĬ
    0.12
    鼶éĥ¨ä»¶
    0.12
    å·¥åİĤ
    0.11
    殿ä¸ĭ
    0.10
    _ISO
    0.10
    丰çĶ°
    0.10
    çĶŁäº§
    0.10
    è´¨éĩı管çIJĨ
    0.10
    âľª
    0.09
    ä¸ĭ游
    0.09
    Activations Density 0.085%

    No Known Activations