© 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. 52023
    Prev
    Next
    INDEX
    Explanations

    Cape Cod Canal

    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
    atan
    -0.10
    arth
    -0.10
    驾é©Ń
    -0.10
    ä»İä¸ļ
    -0.09
    REEN
    -0.09
    èĽĻ
    -0.09
    çĺ
    -0.09
    çļĩåĨł
    -0.09
    cth
    -0.09
    为ä¹ĭ
    -0.09
    POSITIVE LOGITS
    deo
    0.09
    åįĬå²Ľ
    0.09
    å²Ľ
    0.09
    èµĽ
    0.09
    auce
    0.09
    pent
    0.09
    mpl
    0.08
    gie
    0.08
    ç£Ĭ
    0.08
    éĢĶ
    0.08
    Activations Density 0.003%

    No Known Activations