© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 58597
    Prev
    Next
    INDEX
    Explanations

    God, Allah, creator

    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
     SEE
    -0.09
    uta
    -0.08
    ÙĬÙĦÙĬ
    -0.08
    ä¸Ŀ
    -0.08
    è®®
    -0.08
     Sans
    -0.07
     extrav
    -0.07
     Kö
    -0.07
     kind
    -0.07
    stead
    -0.07
    POSITIVE LOGITS
    ä¸Ĭå¸Ŀ
    0.18
    å¤©åľ°
    0.14
     God
    0.13
    God
    0.12
     اÙĦÙĦÙĩ
    0.12
    天åłĤ
    0.11
    dio
    0.11
     GOD
    0.11
     Allah
    0.11
     سبØŃاÙĨÙĩ
    0.11
    Activations Density 0.066%

    No Known Activations