© 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. 21532
    Prev
    Next
    INDEX
    Explanations

    prove or demonstrate something

    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
    åĸľ
    -0.12
    _sl
    -0.08
    -sl
    -0.08
    æıĨ
    -0.08
    åĸľæĤ¦
    -0.08
    å¯ĨåĪĩ
    -0.08
    çĭ¬å®¶
    -0.08
     Antar
    -0.08
    utors
    -0.08
    éĶģ
    -0.08
    POSITIVE LOGITS
    è¯ģæĺİ
    0.14
     prove
    0.12
    èŃīæĺİ
    0.11
    æľīèĥ½åĬĽ
    0.10
     demonstrate
    0.10
    æľīä»·åĢ¼
    0.10
    prove
    0.09
     proving
    0.09
     proves
    0.09
    鸳
    0.09
    Activations Density 0.028%

    No Known Activations