© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 34789
    Prev
    Next
    INDEX
    Explanations

    apparently + conjunction/preposition

    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
     myself
    -0.12
    æĪijä¼ļ
    -0.11
    çĨŁæĤīçļĦ
    -0.10
    å½ĵæĪij
    -0.09
    æľ¬äºº
    -0.09
    åľ¨æĪijçļĦ
    -0.08
    ä¸įçŁ¥ä¸įè§ī
    -0.08
    对èĩªå·±
    -0.08
    çĨŁæĤī
    -0.08
    éĹ®éģĵ
    -0.08
    POSITIVE LOGITS
    æį®è¯´
    0.18
    ãĤīãģĹãģĦ
    0.15
     reportedly
    0.14
     allegedly
    0.14
     supposedly
    0.13
     apparently
    0.12
     evidently
    0.12
     Apparently
    0.12
    Apparently
    0.12
    æį®
    0.12
    Activations Density 0.241%

    No Known Activations