© 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. 11891
    Prev
    Next
    INDEX
    Explanations

    better followed by verb

    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
    å±ħçĦ¶
    -0.10
    欲
    -0.10
    ä½ķå¿ħ
    -0.09
    ÙĬÙģ
    -0.09
    çī¹éĤĢ
    -0.09
    å¾Ģå¹´
    -0.09
    åİŁèijĹ
    -0.09
    澡
    -0.08
    orld
    -0.08
    onium
    -0.08
    POSITIVE LOGITS
    骥
    0.10
    éĹ®éĹ®
    0.09
    åIJ¦åĪĻ
    0.09
    è®¤çľŁåŃ¦ä¹ł
    0.09
    ellen
    0.09
    ä»İäºĭ
    0.09
    à¹Ĥà¸Ĺร
    0.08
    à¸Ħล
    0.08
    _rg
    0.08
    è°Īè°Ī
    0.08
    Activations Density 0.005%

    No Known Activations