© 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. 32121
    Prev
    Next
    INDEX
    Explanations

    includes, means, sense

    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
    è´¨
    -0.09
    enberg
    -0.08
     perch
    -0.08
    åĬŁå¾·
    -0.08
    å°±ä¸į
    -0.08
    åĬ²
    -0.08
    åĽłä¸ºå®ĥ
    -0.08
    åĽłä¸ºæĪij
    -0.08
    orest
    -0.08
    åıªèĥ½è¯´
    -0.08
    POSITIVE LOGITS
    åĮħæĭ¬
    0.14
    æĮĩçļĦæĺ¯
    0.13
    åħ¶ä¸ŃåĮħæĭ¬
    0.12
    Ø´ÙħÙĦ
    0.11
    æĺ¯æĮĩ
    0.11
    主è¦ģåĮħæĭ¬
    0.11
     includes
    0.11
     INCLUDE
    0.10
    涵çĽĸ
    0.10
    涵çĽĸäºĨ
    0.10
    Activations Density 0.133%

    No Known Activations