© 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. 10232
    Prev
    Next
    INDEX
    Explanations

    battlefield fields greenhouse methane

    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
    å½ĵåľ°æĶ¿åºľ
    -0.12
    åĪ°ä½į
    -0.11
    对å¤ĸ
    -0.10
    éĴĬ
    -0.10
    éºĴéºŁ
    -0.10
    æİĺ
    -0.09
    çī¹åĪ«æĺ¯
    -0.09
    çı©
    -0.09
    ç©¿è¡£
    -0.09
    æ¯ĶåĪ©
    -0.09
    POSITIVE LOGITS
    ç±´
    0.08
     copp
    0.08
    dl
    0.08
     váºŃn
    0.08
    ç²¹
    0.07
    åĽļ
    0.07
    /by
    0.07
    ย
    0.07
    çĨŁæĤīçļĦ
    0.07
    uve
    0.07
    Activations Density 0.002%

    No Known Activations