© 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. 34931
    Prev
    Next
    INDEX
    Explanations

    What questions follow

    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
    çĮİ
    -0.09
    ä¾Ŀ次
    -0.09
    åIJij举
    -0.08
    åı¦ä¸ĢåįĬ
    -0.08
    çĶ©
    -0.08
    æĥħä¾£
    -0.08
    çģ«çĥ§
    -0.08
    æįĭ
    -0.07
    IMA
    -0.07
    ç»ĦæĪIJ
    -0.07
    POSITIVE LOGITS
    åŃ©åŃIJ
    0.14
    åŃ©åŃIJçļĦ
    0.13
    çļĦåŃ©åŃIJ
    0.12
    çĶ·åŃ©
    0.12
    çĶ·åŃ©åŃIJ
    0.12
    让åŃ©åŃIJ
    0.11
    å°ıçĶ·åŃ©
    0.11
    åıijèĤ²
    0.11
    æĤ£åĦ¿
    0.11
    让她
    0.10
    Activations Density 0.063%

    No Known Activations