© 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. 3784
    Prev
    Next
    INDEX
    Explanations

    one of the

    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
    rema
    -0.11
    æľīä¸Ģå®ļçļĦ
    -0.09
    åĢ¨
    -0.09
    çŃ
    -0.09
    è¦ģä¹Ī
    -0.09
    绯
    -0.09
    æĥħåĨµè¿Ľè¡Į
    -0.09
    æIJª
    -0.09
    à¸Ńà¸ģ
    -0.08
    好åIJ§
    -0.08
    POSITIVE LOGITS
    åİŁåĽłæĺ¯
    0.14
    éĹ®é¢ĺæĺ¯
    0.13
    çī¹çĤ¹æĺ¯
    0.12
    æľĢéĩįè¦ģçļĦ
    0.11
    å°±æĺ¯è¦ģ
    0.11
    缮çļĦæĺ¯
    0.11
    åĢ¼å¾Ĺ注æĦı
    0.11
    åħ³éĶ®æĺ¯
    0.10
     reason
    0.10
    æľĢéĩįè¦ģ
    0.10
    Activations Density 0.092%

    No Known Activations