© 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. 61162
    Prev
    Next
    INDEX
    Explanations

    garner, elicited, attention

    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
    yna
    -0.10
    elon
    -0.10
    çħ
    -0.10
    ÙĨÙħ
    -0.09
    é¢IJ
    -0.09
    ä¸Ģ件äºĭ
    -0.08
    å®ļäºĨ
    -0.08
    -plane
    -0.08
     Stout
    -0.08
    asts
    -0.08
    POSITIVE LOGITS
    ously
    0.11
    åIJĮæĥħ
    0.11
    forth
    0.10
    è¶³å¤ŁçļĦ
    0.10
     attention
    0.10
    麾
    0.09
    亲æĥħ
    0.09
    è¶ĬæĿ¥è¶Ĭé«ĺ
    0.09
     вла
    0.09
    ılmÄ±ÅŁ
    0.09
    Activations Density 0.005%

    No Known Activations