© 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. 18591
    Prev
    Next
    INDEX
    Explanations

    museums, gardens, maritime, state, events

    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
    寡
    -0.10
    éªĦ
    -0.10
    ç±³é¥Ń
    -0.09
    æ°ijæĶ¿
    -0.09
     inex
    -0.09
    积èĵĦ
    -0.09
    ä¸įæĸŃæī©å¤§
    -0.09
    è¿ĩ硬
    -0.09
    积累äºĨ
    -0.08
    åĺı
    -0.08
    POSITIVE LOGITS
    å±ķ示
    0.12
    è¿ijè·Ŀ离
    0.10
    å±ķåĩº
    0.10
    åıĤè§Ĥ
    0.10
    äºĴåĬ¨
    0.09
    å±ķè§Ī
    0.09
    æĬ«éľ²
    0.09
     interactive
    0.09
    éĻĪåĪĹ
    0.09
    æ¡£
    0.08
    Activations Density 0.118%

    No Known Activations