© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 35604
    Prev
    Next
    INDEX
    Explanations

    using past tense auxiliary 'have'

    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
    å°±ç®Ĺ
    -0.10
    ippo
    -0.09
    tron
    -0.08
    åĿª
    -0.08
    å®ĥçļĦ
    -0.08
    åĵªæĢķ
    -0.08
    æ§Ľ
    -0.08
    çľ¼åħī
    -0.08
    ç§Ģ
    -0.08
    è¦ģä¹Ī
    -0.07
    POSITIVE LOGITS
    æĺ¯åľ¨
    0.11
    使çĶ¨çļĦ
    0.11
    èĸ¤
    0.10
    主è¦ģä»İäºĭ
    0.10
    主è¦ģæĺ¯
    0.09
    çķ¶æĻĤ
    0.09
    å½ĵæŶ
    0.09
    agic
    0.09
    沿海
    0.09
    ç¡®
    0.09
    Activations Density 0.574%

    No Known Activations