© 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. 37853
    Prev
    Next
    INDEX
    Explanations

    form of arrangement

    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
    DTD
    -0.08
    éļĶ
    -0.08
    bard
    -0.08
     informed
    -0.08
    late
    -0.08
    ORS
    -0.07
    åħ³éĶ®æĺ¯
    -0.07
    çľĩ
    -0.07
    ä»·åĢ¼éĵ¾
    -0.07
    ä½İè°ĥ
    -0.07
    POSITIVE LOGITS
    é¹Ħ
    0.10
     tán
    0.10
    çĶļèĩ³è¿ĺ
    0.10
    模仿
    0.09
    éĿ¡
    0.09
     frem
    0.09
     Kitt
    0.09
    ä¸Ĭåİ»
    0.09
    åıªæĥ³
    0.09
    /Instruction
    0.09
    Activations Density 0.109%

    No Known Activations