© 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. 23852
    Prev
    Next
    INDEX
    Explanations

    high heat, infrared radiation

    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
    æĦ§
    -0.10
    opoulos
    -0.09
     LU
    -0.09
    æĦŁæ¿Ģ
    -0.09
    _RA
    -0.09
    åıĪ好
    -0.08
    shouldBe
    -0.08
    .lucene
    -0.08
    .dex
    -0.08
    ä¹Ķ
    -0.08
    POSITIVE LOGITS
    çħİ
    0.10
    ãģĤãĤĮ
    0.09
    èĴ¸æ±½
    0.09
    çĥĪ
    0.09
    çĩ
    0.09
    çĥ«
    0.09
    kek
    0.09
    çĥ¹
    0.09
    åIJĵ
    0.09
    éĶħ
    0.09
    Activations Density 0.144%

    No Known Activations