© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51677
    Prev
    Next
    INDEX
    Explanations

    pronouns followed by verbs

    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
    è½»æĺĵ
    -0.09
     Gloss
    -0.09
    åĽŀå¤į
    -0.09
    çĿ¬
    -0.08
    ç»°
    -0.08
    æ½ŀ
    -0.08
    respond
    -0.08
    ç¶ļãģįãĤĴèªŃãĤĢ
    -0.08
    aver
    -0.08
    议论
    -0.08
    POSITIVE LOGITS
    çļĦçIJĨçĶ±
    0.12
    åħ·ä½ĵ
    0.11
    çIJĨçĶ±
    0.11
    ä¹ŁçŁ¥éģĵ
    0.10
    ä¹ŁåĽłæѤ
    0.10
    _then
    0.09
    åIJİæĿ¥
    0.09
     Kem
    0.09
    igua
    0.09
     cuff
    0.09
    Activations Density 0.120%

    No Known Activations