© 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. 9646
    Prev
    Next
    INDEX
    Explanations

    so + subjective clauses

    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
    é¹ŀ
    -0.12
    大è¡Ĺ
    -0.10
    åĽłä¸ºæĪij们
    -0.10
    åĽłä¸ºä½ł
    -0.10
    æĸ¼æĺ¯
    -0.09
    好åĥıæĺ¯
    -0.09
    ä¹ĭæīĢ以
    -0.09
    äºİæĺ¯
    -0.09
    .getValueAt
    -0.09
    æľ¬åľŁ
    -0.09
    POSITIVE LOGITS
    oon
    0.09
    -called
    0.09
    å¿ħ
    0.09
    ä½ķå¿ħ
    0.08
    bay
    0.08
    .tm
    0.08
    èĩªçĦ¶
    0.08
    cpf
    0.07
     Cup
    0.07
    ollo
    0.07
    Activations Density 0.038%

    No Known Activations