© 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. 20744
    Prev
    Next
    INDEX
    Explanations

    makes people or things

    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
    clip
    -0.09
    hower
    -0.08
    åħ±æľī
    -0.08
     crush
    -0.07
    åĮĸ
    -0.07
    为ä¸Ģä½ĵ
    -0.07
     quo
    -0.07
    odka
    -0.07
     nothing
    -0.07
    anked
    -0.07
    POSITIVE LOGITS
    ä¼Łå¤§
    0.13
    绩
    0.11
    æĺİæĺİ
    0.11
    è¿Ļä¹Īåģļ
    0.11
    è¿Ļ两ç§į
    0.11
    éĤ£ä¹Īå¤ļ
    0.10
    éĤ£æ®µ
    0.10
    è¿Ļ家ä¼Ļ
    0.10
    è¯įæĿ¡
    0.10
    éķ¿éĢĶ
    0.10
    Activations Density 0.177%

    No Known Activations