© 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. 8435
    Prev
    Next
    INDEX
    Explanations

    these + plural nouns

    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
    çĦī
    -0.10
    èĶļ
    -0.09
    åIJģ
    -0.09
    amu
    -0.09
    ä¸Ĭä¸ĭ
    -0.08
    eco
    -0.08
    åľĥ
    -0.08
    é¾Ł
    -0.08
    çIJĩ
    -0.08
    иÑģк
    -0.08
    POSITIVE LOGITS
    ipse
    0.10
    è¿Ļæī¹
    0.10
    æĬĬè¿ĻäºĽ
    0.09
    ä½ĵéĩı
    0.09
    ä¼ģä¸ļåľ¨
    0.09
    LOSS
    0.09
    è¿ĻäºĽä¸ľè¥¿
    0.09
    è¿ĻäºĽéĥ½æĺ¯
    0.09
    è¦ģ害
    0.09
    доÑĢ
    0.09
    Activations Density 0.044%

    No Known Activations