© 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. 20775
    Prev
    Next
    INDEX
    Explanations

    course work

    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
    éĻŁ
    -0.09
    official
    -0.09
    éĽĦ
    -0.08
    å¾ģ
    -0.08
    _coverage
    -0.08
    åĩĮ
    -0.08
    Coverage
    -0.08
     Coverage
    -0.08
    è¦ĨçĽĸ
    -0.08
     coverage
    -0.08
    POSITIVE LOGITS
    ä¸įçĪ±
    0.10
    åįķ纯çļĦ
    0.09
    AdapterManager
    0.09
    onnement
    0.08
    ä¸įå°ıå¿ĥ
    0.08
    alom
    0.08
    为人
    0.08
    ä¹IJåĽŃ
    0.08
    ¢åįķ
    0.08
    .masks
    0.08
    Activations Density 0.221%

    No Known Activations