© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 22391
    Prev
    Next
    INDEX
    Explanations

    to + verb

    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
    Negative Logits
    æĹ¢æľī
    -0.10
    æĪIJçĨŁçļĦ
    -0.09
    éģŃåıĹ
    -0.09
    è¿Ļç¯ĩ
    -0.08
    æĦı大
    -0.08
    çĥŃå¿ĥ
    -0.08
     Probe
    -0.08
    æīĢè°ĵçļĦ
    -0.08
     бÑĭÑĤÑĮ
    -0.08
    _REGISTRY
    -0.08
    POSITIVE LOGITS
    æĬĬå®ĥ
    0.24
    å°Ĩåħ¶
    0.19
    使ä¹ĭ
    0.18
    对åħ¶è¿Ľè¡Į
    0.18
    让å®ĥ
    0.17
    å®ĥæĺ¯
    0.16
    为ä¹ĭ
    0.15
    使åħ¶
    0.15
    对åħ¶
    0.14
    å®ĥåı¯ä»¥
    0.14
    Activations Density 0.382%

    No Known Activations