© 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. 36722
    Prev
    Next
    INDEX
    Explanations

    before

    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
    ingo
    -0.10
    åħµ
    -0.09
    oose
    -0.09
    è¦ģä¹Ī
    -0.09
    ilot
    -0.08
    çĮ´
    -0.08
    .unlock
    -0.08
    adel
    -0.08
     RCA
    -0.08
    è°Ķ
    -0.08
    POSITIVE LOGITS
    ä¸įå¤ļ
    0.11
    (before
    0.11
    ä¸Ģå®ļè¦ģ
    0.11
    æľīä»»ä½ķ
    0.10
    -before
    0.10
    è¿ĻçĤ¹
    0.09
    对人ä½ĵ
    0.09
    äºĨè§£æĽ´å¤ļ
    0.09
    详ç»ĨäºĨ解
    0.09
     ÑģовÑģем
    0.09
    Activations Density 0.022%

    No Known Activations