© 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. 56421
    Prev
    Next
    INDEX
    Explanations

    plot arcs and conclusions

    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
    人身
    -0.09
    ç±ģ
    -0.09
    ä»İä¸Ń
    -0.09
    Å¡t
    -0.09
    mong
    -0.09
    å¾ľ
    -0.09
    æ²IJæµ´
    -0.09
    æĿµ
    -0.09
    èĨº
    -0.09
    avings
    -0.08
    POSITIVE LOGITS
    ç»ĵå°¾
    0.15
    åī§æĥħ
    0.14
    æĥħèĬĤ
    0.13
    æīĢæľīæĥħèĬĤ
    0.12
     plot
    0.12
    é«ĺæ½®
    0.12
    交代
    0.11
    ä¸Ģç¬Ķ
    0.10
    ç»ĪçĤ¹
    0.10
    éĺ´è°ĭ
    0.10
    Activations Density 0.087%

    No Known Activations