© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 3146
    Prev
    Next
    INDEX
    Explanations

    solution methods

    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
    ç®Ģ称
    -0.09
    æŦ
    -0.09
     loft
    -0.09
    é¢IJ
    -0.08
    åħ³éĶ®æŶåĪ»
    -0.08
    èĪ¬
    -0.08
    æ¼¾
    -0.08
    æİ¥åĬĽ
    -0.08
    ç½ijä¸Ĭ
    -0.08
    åij¼
    -0.08
    POSITIVE LOGITS
    æĽ´å¤ļçļĦæĺ¯
    0.10
    鹧
    0.09
    매
    0.09
    meld
    0.09
    един
    0.09
    æľīå¾Ī大çļĦ
    0.09
    quired
    0.08
    æĪijå°±
    0.08
    _BOUND
    0.08
    å®īåħ¨ä¿Ŀéļľ
    0.08
    Activations Density 0.492%

    No Known Activations