© 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. 63649
    Prev
    Next
    INDEX
    Explanations

    Blair, Girl, Academy, waiting

    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
    æī¶
    -0.11
    æ®ĸ
    -0.10
    åı°
    -0.10
    ÙħصاÙĦØŃ
    -0.09
    tic
    -0.08
    æį§
    -0.08
    åIJ¬è¯´
    -0.08
    å¾ĭ
    -0.08
    æĭĽçīĮ
    -0.08
     Creator
    -0.08
    POSITIVE LOGITS
    éĵł
    0.09
    uge
    0.09
    é¹Ĭ
    0.08
    åĽº
    0.08
    ember
    0.08
    ÙĩÙĨ
    0.08
     votes
    0.08
    表çĻ½
    0.08
    æĭįæĭį
    0.08
    æ¯ķä¸ļçĶŁ
    0.08
    Activations Density 0.127%

    No Known Activations