© 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. 8255
    Prev
    Next
    INDEX
    Explanations

    words ending in "ana" and "ol"

    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
    ifu
    -0.09
    dess
    -0.09
    绸
    -0.09
     stan
    -0.08
    路段
    -0.08
    lix
    -0.08
    icho
    -0.08
    ipa
    -0.08
    ignum
    -0.08
     Stan
    -0.08
    POSITIVE LOGITS
     Leban
    0.09
    classic
    0.09
    è®·
    0.09
    çļĦ带é¢Ĩä¸ĭ
    0.09
    å·§å¦Ļ
    0.09
    onas
    0.08
     walmart
    0.08
    åIJįèªī
    0.08
    çĶµè§Ĩæľº
    0.08
     Ñģебе
    0.08
    Activations Density 0.054%

    No Known Activations