© 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. 20039
    Prev
    Next
    INDEX
    Explanations

    plant and species names

    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
    大åħ¨
    -0.09
     Jerseys
    -0.09
    ests
    -0.09
    çĸ½
    -0.09
    èĿł
    -0.09
    .ld
    -0.09
    æĮ¯ãĤĬ
    -0.09
    æ¨¡æł·
    -0.09
    æ¦ī
    -0.08
    linger
    -0.08
    POSITIVE LOGITS
    æĽĻ
    0.09
    滨海
    0.09
    .ta
    0.09
    ä»°
    0.08
    ä»ĺè´¹
    0.08
    nation
    0.08
    é»İæĺİ
    0.08
    éĨĴ
    0.08
    æĴij
    0.08
    å°¤
    0.08
    Activations Density 0.015%

    No Known Activations