© 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. 31835
    Prev
    Next
    INDEX
    Explanations

    teaching, learning, and rewards

    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
    åıij表äºĨ
    -0.10
    èī¾
    -0.09
     rival
    -0.09
    ãģĬãģĦ
    -0.09
    éĢIJ
    -0.09
    kr
    -0.09
    è¿Īè¿Ľ
    -0.08
    èĨ³
    -0.08
    åģľæĶ¾
    -0.08
    è¶Ĭæĺ¯
    -0.08
    POSITIVE LOGITS
    带æĿ¥çļĦ
    0.10
    带ç»Ļ
    0.10
    åģļçļĦäºĭæĥħ
    0.10
    éĢłæĪIJçļĦ
    0.10
    ä½ľèĢħæīĢæľī
    0.09
    UME
    0.09
     Ptr
    0.09
    å¼ķèµ·çļĦ
    0.09
    abant
    0.09
    æıIJä¾ĽçļĦ
    0.09
    Activations Density 0.074%

    No Known Activations