© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 22845
    Prev
    Next
    INDEX
    Explanations

    fortification and storage

    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
    çľĭ书
    -0.10
    亲
    -0.10
    æĪIJæŀľè½¬åĮĸ
    -0.09
    çļĦçľ¼åħī
    -0.09
    ç¾İçļĦ
    -0.09
    親
    -0.09
    rame
    -0.09
    ç¾ģ
    -0.08
    ĪæĿĥ
    -0.08
    èĮ§
    -0.08
    POSITIVE LOGITS
    çļĦåķĨåĵģ
    0.10
    éļIJå½¢
    0.09
    .addListener
    0.09
    è¡¢
    0.09
    .Join
    0.09
    çĶµåŃIJ
    0.09
    cri
    0.08
    joining
    0.08
    æ¦ķ
    0.08
    Join
    0.08
    Activations Density 0.162%

    No Known Activations