© 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. 20888
    Prev
    Next
    INDEX
    Explanations

    places and names

    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
    çĹ¹
    -0.10
    ereg
    -0.09
    CHANT
    -0.09
    ëŀŃ
    -0.09
    åĴĮå¹³
    -0.09
    åĬ±å¿Ĺ
    -0.09
    å¼ĢæľĹ
    -0.09
    GridColumn
    -0.08
    ä¸įåı¯éģ¿åħį
    -0.08
    æģª
    -0.08
    POSITIVE LOGITS
     Worldwide
    0.14
    ว
    0.13
    w
    0.13
     William
    0.13
    W
    0.12
     W
    0.12
    V
    0.12
    µ
    0.11
    v
    0.11
    0
    0.11
    Activations Density 0.436%

    No Known Activations