© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10325
    Prev
    Next
    INDEX
    Explanations

    el- word beginnings

    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
    iani
    -0.10
     Trev
    -0.09
    dem
    -0.08
    éĥ¯
    -0.08
    st
    -0.08
    _startup
    -0.08
    ί
    -0.08
    å¡į
    -0.08
    8
    -0.08
    cook
    -0.08
    POSITIVE LOGITS
    0.13
    ä¸Ģçīĩ
    0.10
    CISION
    0.09
    ä¸Ģæŀ¶
    0.09
    ÑģÑĥ
    0.09
    äºī龸
    0.09
    éĵİ
    0.09
    essler
    0.09
    ä¸Ģçķª
    0.09
    ä¸ĢåłĨ
    0.09
    Activations Density 0.141%

    No Known Activations