© 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. 52611
    Prev
    Next
    INDEX
    Explanations

    author, model, corporation, documentary

    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
    ç±³é¥Ń
    -0.10
    Hur
    -0.09
    _TC
    -0.09
    çĻŀ
    -0.09
     Hur
    -0.08
    å¼ŁåŃIJ
    -0.08
    ä¸įå°ij
    -0.08
     immediate
    -0.08
    ä¸ŃéĹ´
    -0.08
    èij«èĬ¦
    -0.08
    POSITIVE LOGITS
    没人
    0.11
    æĹłäºº
    0.09
    æģ°å¥½
    0.08
    æīĢæľī人éĥ½
    0.08
    yat
    0.08
    èħķ
    0.08
     hei
    0.08
    âĿ®
    0.08
    æĺĤè´µ
    0.08
    çĽijæĬ¤
    0.08
    Activations Density 0.214%

    No Known Activations