© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50910
    Prev
    Next
    INDEX
    Explanations

    inspiration/fodder

    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
    å²ĺ
    -0.10
    ä¸Ģéģĵ
    -0.09
    é¢ĨåĨĽ
    -0.09
    æī°ä¹±
    -0.08
     sadd
    -0.08
    æIJºå¸¦
    -0.08
    å¾ĺå¾Ĭ
    -0.08
    éº
    -0.08
    ÑģÑħод
    -0.08
    ê²°
    -0.08
    POSITIVE LOGITS
    ç´łæĿIJ
    0.26
    é¢ĺæĿIJ
    0.15
    ãĥįãĤ¿
    0.14
    åĪĽä½ľ
    0.11
    æºIJæºIJ
    0.11
     inspiration
    0.11
    æŀĦæĢĿ
    0.10
    åı¯ä¾Ľ
    0.10
     fodder
    0.10
    è¯Ŀé¢ĺ
    0.10
    Activations Density 0.092%

    No Known Activations