© 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. 9018
    Prev
    Next
    INDEX
    Explanations

    public health, responsibilities, utility

    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
    zik
    -0.10
    è¾±
    -0.09
    å¼ĵ
    -0.08
    èĤĦ
    -0.08
    _revision
    -0.08
    éĺ´éĺ³
    -0.08
     hak
    -0.07
    æĦŁ
    -0.07
    ä¼ĺ
    -0.07
    nty
    -0.07
    POSITIVE LOGITS
    åħ¬åħ±æľįåĬ¡
    0.14
    åħ¬çĽĬæĢ§
    0.14
    åħ¬åħ±
    0.14
    actory
    0.11
    æĻ®æĥł
    0.11
    åıĹçĽĬ
    0.11
     благ
    0.10
    åħ¬çĽĬ
    0.10
    çħ§äº®
    0.10
    大家åĪĨ享
    0.10
    Activations Density 0.071%

    No Known Activations