© 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. 50363
    Prev
    Next
    INDEX
    Explanations

    temperature, circulation, stress, concentration

    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
    åĬłå·¥åİĤ
    -0.10
    åıijåĬ¨
    -0.10
    åĶ§
    -0.09
    没æľīæĥ³åĪ°
    -0.09
    çļĦ认è¯Ĩ
    -0.09
    æ¡ĥèĬ±
    -0.09
    æ»Ł
    -0.09
    èľ¥
    -0.09
    å¼łæī¬
    -0.09
    å¿ĺ
    -0.09
    POSITIVE LOGITS
    æ¯ķä¸ļ
    0.08
    ents
    0.08
    roid
    0.08
    isters
    0.08
    inel
    0.08
    åĽ°
    0.08
     tá»ij
    0.07
    /Common
    0.07
     sink
    0.07
    ENTS
    0.07
    Activations Density 0.120%

    No Known Activations