© 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. 21432
    Prev
    Next
    INDEX
    Explanations

    Office and Services

    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
     Sandwich
    -0.09
    åĪºå®¢
    -0.09
    å¯Ħæīĺ
    -0.08
    ä¼ĺèī¯
    -0.08
    åīįèĢħ
    -0.08
    磨
    -0.08
    éĶ·
    -0.08
     sandwich
    -0.08
    åıijæĮ¥
    -0.08
     ÑĦоÑĢ
    -0.08
    POSITIVE LOGITS
    EMU
    0.10
    æ¡ĮéĿ¢
    0.09
    stub
    0.09
    iais
    0.09
    ãģIJ
    0.08
    .ask
    0.08
     Depot
    0.08
    iangle
    0.08
     Nuggets
    0.08
    riter
    0.08
    Activations Density 0.002%

    No Known Activations