© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20670
    Prev
    Next
    INDEX
    Explanations

    names of people and places

    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
    鹿
    -0.10
    éºĵ
    -0.09
    æĭ±
    -0.09
    åĪ¨
    -0.09
    åħ³åı£
    -0.09
    çĥĪ
    -0.08
    ä¸ĢæĿ¡é¾Ļ
    -0.08
    oleon
    -0.08
    .SIZE
    -0.08
     سÙĨ
    -0.08
    POSITIVE LOGITS
    ваÑĤ
    0.10
    ardi
    0.10
    çĻ½éĽª
    0.09
     Fog
    0.09
    washing
    0.09
    祸
    0.08
    妯
    0.08
     GOT
    0.08
    å¿ĥæĥ³
    0.08
    aned
    0.08
    Activations Density 0.007%

    No Known Activations