© 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. 22021
    Prev
    Next
    INDEX
    Explanations

    sub-Saharan Africa

    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
    stab
    -0.09
    aura
    -0.09
    apus
    -0.09
    çĶ³è´Ń
    -0.09
    驾é©Ń
    -0.09
    éĹªåħī
    -0.09
    ERM
    -0.09
    ANGER
    -0.09
    INLINE
    -0.08
    /vendor
    -0.08
    POSITIVE LOGITS
     African
    0.09
    åĤ¬
    0.09
     (*)(
    0.09
    ders
    0.09
    éĿŀæ´²
    0.08
    硼
    0.08
    5
    0.08
    çݯå¢ĥä¸Ń
    0.08
     Rue
    0.08
    3
    0.08
    Activations Density 0.006%

    No Known Activations