© 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. 50931
    Prev
    Next
    INDEX
    Explanations

    starting phrases of texts

    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
    imar
    -0.09
    _RC
    -0.09
    æľŁåĨħ
    -0.08
    elder
    -0.08
    лÑĭ
    -0.08
    -ish
    -0.08
    è¿Ī
    -0.08
    æ¶Īè´¹åįĩ级
    -0.08
    åĪ¶èį¯
    -0.08
    nis
    -0.08
    POSITIVE LOGITS
    abwe
    0.10
    è°ĥåĬ¨
    0.09
    寸
    0.09
    个å°ı
    0.09
     Sink
    0.09
    ä¼ļ产çĶŁ
    0.08
     exclaimed
    0.08
     Pos
    0.08
    iquement
    0.08
    âĺı
    0.08
    Activations Density 0.135%

    No Known Activations