© 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. 50943
    Prev
    Next
    INDEX
    Explanations

    state and local laws

    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
    çıĪ
    -0.10
    èĬ·
    -0.09
    驺
    -0.09
    æĦŁåºĶ
    -0.09
    线æĿ¡
    -0.09
    pet
    -0.08
    odel
    -0.08
    ë³ij
    -0.08
     hin
    -0.08
    è¿ĩæĪ·
    -0.08
    POSITIVE LOGITS
    åĢĭ人
    0.10
    ãģķãģĪ
    0.09
    两级
    0.09
    身ä½ĵåģ¥åº·
    0.09
    .Hex
    0.09
    èĩªèº«çļĦ
    0.09
    reb
    0.09
    åħ·æľīèī¯å¥½
    0.09
    个人
    0.09
    ë³µ
    0.08
    Activations Density 0.134%

    No Known Activations