© 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. 20195
    Prev
    Next
    INDEX
    Explanations

    social groups

    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·´æĭī
    -0.10
    èģ²æĺİ
    -0.10
    [opt
    -0.10
    纤
    -0.10
    COPE
    -0.10
    éļ°
    -0.09
    ä¹Łä¸įä¼ļ
    -0.09
    åĬłåĽº
    -0.09
    纪å§Ķ书记
    -0.09
    å¼Ģåħ·
    -0.09
    POSITIVE LOGITS
    ä¸IJ
    0.12
    为é¦ĸ
    0.09
    çĪ¬
    0.08
    membership
    0.08
    WS
    0.08
    ç«
    0.08
    åĬĪ
    0.08
    Formation
    0.08
    elpers
    0.08
    erties
    0.08
    Activations Density 0.052%

    No Known Activations