© 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. 36094
    Prev
    Next
    INDEX
    Explanations

    Itanium, sensation, orders, camp, television

    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
    åıĪ好
    -0.10
    åĵįèµ·
    -0.10
    çĪ±ä¸Ĭ
    -0.09
    åĬ¡
    -0.08
    èĤĮèĤ¤
    -0.08
     utmost
    -0.08
    æŃ£å½ĵ
    -0.08
    Experts
    -0.08
    æĺ¯æĢİæł·
    -0.08
    轩
    -0.08
    POSITIVE LOGITS
    åİŁæľīçļĦ
    0.16
    åİŁæľī
    0.14
    åİŁåħĪ
    0.13
    åİŁæĿ¥çļĦ
    0.12
    æŧ
    0.11
    èĢĮæĺ¯
    0.11
     пÑĢеж
    0.11
    è¿ĩå¤ļ
    0.11
    åİŁä¾Ĩ
    0.11
    以å¾Ģ
    0.10
    Activations Density 0.285%

    No Known Activations