© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9274
    Prev
    Next
    INDEX
    Explanations

    not so + adjective

    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
    ãģĹãģ¾ãģĦ
    -0.09
    趣
    -0.09
    æĸĩæĺĮ
    -0.08
    å¾Īä¸įéĶĻ
    -0.08
    ç¿Ķ
    -0.08
    çĶļä¹Ī
    -0.08
    å¾Īå¤ļæŶåĢĻ
    -0.08
    åĬ«
    -0.08
    ä¸į妨
    -0.08
    ÙģÙī
    -0.08
    POSITIVE LOGITS
    ä¸İæѤ
    0.09
    unner
    0.09
    евиÑĩ
    0.09
    çĹĽèĭ¦
    0.09
    éĶħ
    0.09
    ä¸İæŶ
    0.09
    åĪ©äºİ
    0.09
    æĺİç¡®äºĨ
    0.09
    ãĥļãĥ³
    0.09
    çĥ¦æģ¼
    0.08
    Activations Density 0.004%

    No Known Activations