© 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. 35010
    Prev
    Next
    INDEX
    Explanations

    use with instructions

    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
    inke
    -0.11
    æģ¢
    -0.08
    лав
    -0.08
    åĵªåĦ¿
    -0.08
    inha
    -0.08
    tape
    -0.08
    ä»Ģä¹Īæĺ¯
    -0.08
    ä»Ģä¹Īä¸ľè¥¿
    -0.08
    åŁł
    -0.08
    imus
    -0.08
    POSITIVE LOGITS
    åIJijä¸Ĭ
    0.10
    æģĴ
    0.09
    èĥŃ
    0.09
    乡
    0.08
    _FAULT
    0.08
    na
    0.08
    è¿Ļå¼ł
    0.08
    åĽºå®ļçļĦ
    0.08
    .bi
    0.08
    ete
    0.08
    Activations Density 0.031%

    No Known Activations