© 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. 51089
    Prev
    Next
    INDEX
    Explanations

    balance and symmetry

    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
    伤害
    -0.08
    GRES
    -0.08
    è¯Ĭ
    -0.08
    ELY
    -0.08
     Balk
    -0.08
    bak
    -0.07
    主任
    -0.07
    æĮ£æīİ
    -0.07
     griev
    -0.07
    Instr
    -0.07
    POSITIVE LOGITS
    çªŁ
    0.12
    份é¢Ŀ
    0.11
    平衡
    0.10
    åŁºæľ¬åİŁåĪĻ
    0.10
    æľĢç¾İ
    0.10
    åĩĨåĪĻ
    0.10
    ä¸įèĩ³äºİ
    0.10
     symmetry
    0.10
     sym
    0.10
    æĦıå¢ĥ
    0.09
    Activations Density 0.051%

    No Known Activations