© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 35806
    Prev
    Next
    INDEX
    Explanations

    then followed by action

    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
    rus
    -0.11
    è¿Ļåĩł
    -0.10
    å¾Īå¿«å°±
    -0.09
    à¹Ħว
    -0.09
    åĪĿ
    -0.09
    TD
    -0.08
    ensed
    -0.08
    pard
    -0.08
    å»ĵ
    -0.08
    æĢİä¹Īçľĭ
    -0.08
    POSITIVE LOGITS
    æīįåı¯ä»¥
    0.24
    æīį
    0.23
    æīįä¼ļ
    0.23
    æīįæĺ¯
    0.22
    æīįæľī
    0.21
    æīįèĥ½
    0.21
    æĪijæīį
    0.21
    æĸ¹åı¯
    0.20
    æīįèĥ½å¤Ł
    0.20
    è¿Ļæīį
    0.18
    Activations Density 0.068%

    No Known Activations