© 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. 30959
    Prev
    Next
    INDEX
    Explanations

    more or less

    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
     ÙĦØ°ÙĦÙĥ
    -0.09
    åĭĻ
    -0.08
    onica
    -0.08
    зд
    -0.08
    rets
    -0.08
    大åĬĽåıijå±ķ
    -0.08
    зв
    -0.08
    天èµĭ
    -0.08
    мел
    -0.08
    åĿĬ
    -0.08
    POSITIVE LOGITS
    åħ¨æĹ¥
    0.13
    ä¸įèĩ³äºİ
    0.12
    æľīåĬ©äºİ
    0.11
    çĨŁæĤīçļĦ
    0.10
    çĨŁæĤī
    0.10
    ä»İèĢĮ
    0.10
     hey
    0.09
     potentially
    0.09
    港åĮº
    0.09
    éĿĽ
    0.09
    Activations Density 0.284%

    No Known Activations