© 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. 37501
    Prev
    Next
    INDEX
    Explanations

    Pamela and variations

    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
    ives
    -0.11
    sson
    -0.10
    çļ¿
    -0.09
    佬
    -0.09
    andr
    -0.09
    人éĢī
    -0.09
    ×ķת
    -0.09
    boro
    -0.09
    paces
    -0.08
    iname
    -0.08
    POSITIVE LOGITS
    о
    0.10
    天ä¸ĭ
    0.10
     меÑĢопÑĢиÑıÑĤиÑı
    0.09
    çľĭæ¸ħ
    0.09
    otec
    0.09
    atical
    0.08
    sexy
    0.08
    handling
    0.08
    à¸Ľà¸£à¸°
    0.08
    esco
    0.08
    Activations Density 0.009%

    No Known Activations