© 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. 3898
    Prev
    Next
    INDEX
    Explanations

    television and related media

    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
    æ®ĩ
    -0.09
    åĩĮ
    -0.08
    åľ¨æĪijåĽ½
    -0.08
    çĿ¹
    -0.08
    Gratis
    -0.08
    常说
    -0.08
     rat
    -0.08
    нÑİ
    -0.08
    称
    -0.08
    .selector
    -0.08
    POSITIVE LOGITS
    çĮ·
    0.11
    è¥ŀ
    0.10
    客åķĨ
    0.09
    åħ³äºİæĪij们
    0.09
    室
    0.09
    æĸĩåĮĸåĴĮ
    0.09
    æĥ¹
    0.09
    éĺľ
    0.08
    isz
    0.08
    Flo
    0.08
    Activations Density 0.015%

    No Known Activations