© 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. 58854
    Prev
    Next
    INDEX
    Explanations

    combine two items

    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
    åĽŀ头
    -0.10
    å®ļä½į
    -0.09
    gpu
    -0.09
    æĢİä¹Ī说
    -0.09
    çī¹åĪ«å£°æĺİ
    -0.09
    ais
    -0.09
    è¿ĺæĺ¯è¦ģ
    -0.09
    нем
    -0.09
    èķ
    -0.09
    orp
    -0.09
    POSITIVE LOGITS
    åľ¨ä¸Ģèµ·
    0.11
    ä»»
    0.09
    åľ¨æ·±åľ³
    0.08
     canonical
    0.08
    åľ¨æİ¥åıĹ
    0.08
     Sug
    0.08
    æīĢæľī
    0.08
    langs
    0.08
    çĽ´è¾¾
    0.08
    å¿ĺ
    0.08
    Activations Density 0.005%

    No Known Activations