© 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. 54006
    Prev
    Next
    INDEX
    Explanations

    commissioned it

    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
    ingham
    -0.09
    ä¸įä»ħåı¯ä»¥
    -0.09
    æĽ´åĬł
    -0.09
    .mi
    -0.09
    ä¸Ģ头
    -0.09
     tomorrow
    -0.08
    ãĤĤãĤīãģĪ
    -0.08
    åłĻ
    -0.08
    å°ĨæĿ¥
    -0.08
    anton
    -0.08
    POSITIVE LOGITS
     originally
    0.15
    è¿Ļä¹Īå¤ļ
    0.14
    éĤ£ä¹Īå¤ļ
    0.13
    å¦ĤæѤ
    0.13
    è¿Ļä¹Īä¹ħ
    0.12
    å½ĵåĪĿ
    0.12
     initially
    0.11
     earlier
    0.11
    è¿Ļä¹Ī
    0.11
    èµ·åĪĿ
    0.10
    Activations Density 0.122%

    No Known Activations