© 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. 36788
    Prev
    Next
    INDEX
    Explanations

    place names ending in 'e'

    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
    ubes
    -0.10
    èĬĻèĵī
    -0.09
    ä¿ħ
    -0.08
    沤
    -0.08
     Reb
    -0.08
    ondon
    -0.08
    ansk
    -0.08
    ä¸Ģä¸ĭåŃIJå°±
    -0.08
    .backend
    -0.08
    arness
    -0.08
    POSITIVE LOGITS
    ä¸ĢåĽ¢
    0.10
    大æĪ·
    0.10
    髯
    0.09
    ache
    0.09
     rumor
    0.09
    èĵij
    0.08
    eenth
    0.08
    缸åħ³è´Łè´£
    0.08
    åĪĨ级
    0.08
    mie
    0.08
    Activations Density 0.116%

    No Known Activations