© 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. 9100
    Prev
    Next
    INDEX
    Explanations

    decision-making and planning

    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
     Cf
    -0.08
    convert
    -0.08
     cord
    -0.08
    æľºåĪ¶
    -0.08
     Rac
    -0.08
    itel
    -0.08
    ros
    -0.08
    é£
    -0.08
    åIJ¬è¯¾
    -0.08
    orig
    -0.07
    POSITIVE LOGITS
    åĨ³çŃĸ
    0.15
    ä¸ĭä¸ĢæŃ¥
    0.12
     decisions
    0.11
    æĶ¹è¿Ľ
    0.11
    失
    0.11
    å¾Ĺåĩº
    0.10
    çŁ¥å·±
    0.10
    æľīéĴĪ对æĢ§
    0.10
     ведÑĮ
    0.10
     decision
    0.09
    Activations Density 0.243%

    No Known Activations