© 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. 58731
    Prev
    Next
    INDEX
    Explanations

    and followed by a word

    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
    å²Ĺä½į
    -0.08
    Õ»
    -0.08
    èķ¨
    -0.08
    æĭĶ
    -0.08
    ll
    -0.08
    说çļĦæĺ¯
    -0.08
    ä¹Łè®¸
    -0.07
    åij¼
    -0.07
    æ¿ij
    -0.07
    EOS
    -0.07
    POSITIVE LOGITS
    è²Ĥ
    0.10
    _ev
    0.09
    éľŃ
    0.09
    prung
    0.09
    .serialization
    0.09
    åħ¶å®ĥéĹ®é¢ĺ
    0.09
    è«
    0.09
    趣
    0.09
    ä»»åij½
    0.09
    .tap
    0.08
    Activations Density 0.334%

    No Known Activations