© 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. 22001
    Prev
    Next
    INDEX
    Explanations

    Luke Skywalker

    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
    åĭĥåĭĥ
    -0.12
    大æĪ·
    -0.10
    èĵ¬åĭĥ
    -0.10
    amp
    -0.10
    r
    -0.09
    nbsp
    -0.09
    line
    -0.08
    è¶ĭåĬ¿
    -0.08
    äºĨ大éĩıçļĦ
    -0.08
    ص
    -0.08
    POSITIVE LOGITS
     Skywalker
    0.12
    overs
    0.11
    busters
    0.10
    ä¸įçĦ¶
    0.10
    avic
    0.10
    ä½łæĢİä¹Ī
    0.10
    anton
    0.09
    âĹ¼
    0.09
     conserv
    0.09
    apter
    0.09
    Activations Density 0.017%

    No Known Activations