© 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. 7406
    Prev
    Next
    INDEX
    Explanations

    magazines and websites

    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
    éĢŀ
    -0.09
    æıĸ
    -0.09
    Nit
    -0.09
    regon
    -0.09
    è´µ
    -0.08
    读æĩĤ
    -0.08
    缸åħ³æĸ°éĹ»
    -0.08
    驳
    -0.08
    饴
    -0.08
    èŀºä¸Ŀ
    -0.08
    POSITIVE LOGITS
    çĶŁæ´»çļĦ
    0.10
    å¿«æīĭ
    0.09
    ä¸įåĬ¨
    0.09
    éĩįçĤ¹é¢ĨåŁŁ
    0.09
    ело
    0.08
    æĸ°ä¸ī
    0.08
    енно
    0.08
     ÑħозÑıй
    0.08
    åģļæ³ķ
    0.08
    家å±ħ
    0.08
    Activations Density 0.021%

    No Known Activations