© 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. 57805
    Prev
    Next
    INDEX
    Explanations

    tall and heights

    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
    æľīæĦı
    -0.10
    ç³»
    -0.09
     crater
    -0.08
    è¶Ĭ
    -0.08
    커
    -0.08
    .yy
    -0.08
    ä¹Ĵä¹ĵ
    -0.08
    åĻ¨æĿIJ
    -0.08
    ÑĤÑĢ
    -0.08
     Mate
    -0.08
    POSITIVE LOGITS
    壮
    0.12
    æłĭ
    0.10
     towering
    0.10
    é³ŀ
    0.10
    é«ĺ楼
    0.10
    æĿī
    0.10
     taller
    0.10
    顶端
    0.10
     tall
    0.10
     heights
    0.10
    Activations Density 0.083%

    No Known Activations