© 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. 8191
    Prev
    Next
    INDEX
    Explanations

    step up or down

    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
    çĽ¼
    -0.10
    æ¯ħåĬĽ
    -0.10
    /on
    -0.09
    æĻ®éĢļè¯Ŀ
    -0.09
    illy
    -0.09
    /std
    -0.09
    飧æĢ§
    -0.09
    éĻħ
    -0.09
    wg
    -0.09
    éĹªçĶµ
    -0.09
    POSITIVE LOGITS
    alon
    0.09
    庵
    0.09
    stakes
    0.09
    .RELATED
    0.08
    åĥı个
    0.08
    ÑĥÑī
    0.08
    æĦĢ
    0.08
    orent
    0.08
    ake
    0.08
     Convention
    0.08
    Activations Density 0.006%

    No Known Activations