© 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. 50143
    Prev
    Next
    INDEX
    Explanations

    anytime soon

    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
    æľĢåĪĿçļĦ
    -0.11
    ä¸Ĭ次
    -0.10
    éļħ
    -0.10
    æľĢåĪĿ
    -0.10
    _rm
    -0.09
    åĪ°å¤Ħ
    -0.09
    ä»İæľª
    -0.09
    éĤ£ä¹Īå¤ļ
    -0.09
    éļĶå£ģ
    -0.09
     spike
    -0.09
    POSITIVE LOGITS
    ä¸įä¹ħ
    0.25
     soon
    0.22
    soon
    0.19
     ÑģкоÑĢо
    0.18
    åį³å°ĨåĪ°æĿ¥
    0.18
    Soon
    0.18
     Soon
    0.17
     upcoming
    0.17
    å¾Īå¿«
    0.17
     forthcoming
    0.16
    Activations Density 0.071%

    No Known Activations