© 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. 5157
    Prev
    Next
    INDEX
    Explanations

    non-exclusive license

    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
    çĭĤ欢
    -0.09
    çĪĨåıij
    -0.09
    ä¸ĵèģĮ
    -0.09
     cú
    -0.09
    åIJĥè¿ĩ
    -0.09
    çħħ
    -0.09
    åĽ½æ°ij
    -0.08
    两天
    -0.08
    çĥŃæĥħ
    -0.08
    项éĵ¾
    -0.08
    POSITIVE LOGITS
    使çĶ¨æĿĥ
    0.12
    åĢŁçĶ¨
    0.10
    使çĶ¨çļĦ
    0.10
    秣èµģ
    0.10
    .Metro
    0.10
    çħ§å°Ħ
    0.09
    ç»Ī身
    0.09
    anted
    0.09
    IBUT
    0.09
    _REUSE
    0.09
    Activations Density 0.089%

    No Known Activations