© 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. 51180
    Prev
    Next
    INDEX
    Explanations

    sustainability and responsibility

    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
    zelf
    -0.12
    夯å®ŀ
    -0.10
    æīĵçĿĢ
    -0.09
    ras
    -0.09
    çķ¶çĦ¶
    -0.09
    åĪ¶çº¦
    -0.09
    ä¸įæĺİçĻ½
    -0.09
    èIJ¥éĢłèī¯å¥½
    -0.09
    çľĭä¸įæĩĤ
    -0.09
    .Foundation
    -0.09
    POSITIVE LOGITS
    æ®·
    0.09
    æĿĸ
    0.08
    Encoded
    0.08
    é¢Ĩ
    0.08
    ification
    0.08
    éĤĪ
    0.08
    çŁ¥æĥħ
    0.08
    -serif
    0.08
    ä¸ĵåijĺ
    0.08
    cep
    0.07
    Activations Density 0.011%

    No Known Activations