© 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. 10525
    Prev
    Next
    INDEX
    Explanations

    requesting more specific information

    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
     Toll
    -0.10
    驽
    -0.09
    åĮħ袱
    -0.09
    å¤ĸæı´
    -0.08
    è¯Ŀ说
    -0.08
    åIJ¸åıĸ
    -0.08
    å¿ĺäºĨ
    -0.08
    iju
    -0.08
    åĿĿ
    -0.08
    åľĨ满å®ĮæĪIJ
    -0.08
    POSITIVE LOGITS
    ç»ĨåĮĸ
    0.17
     specificity
    0.16
    åħ·ä½ĵ
    0.15
    精确
    0.13
    ç»ĨåĪĨ
    0.12
     cụ
    0.12
     конкÑĢеÑĤ
    0.12
     Specific
    0.12
    åħ·ä½ĵçļĦ
    0.12
     Prec
    0.11
    Activations Density 0.099%

    No Known Activations