© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37426
    Prev
    Next
    INDEX
    Explanations

    arranged, arrangement, arriving

    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
    alty
    -0.11
    ãģ¾ãģ¾
    -0.10
    amic
    -0.09
    ows
    -0.09
    ç²²
    -0.09
    -hearted
    -0.08
    æģĻ
    -0.08
    人æ°ijåĮ»éĻ¢
    -0.08
    itus
    -0.08
    aan
    -0.08
    POSITIVE LOGITS
    ments
    0.12
    angement
    0.11
    anged
    0.11
    hythm
    0.11
    ees
    0.10
    iment
    0.09
    æĽ¿ãģĪ
    0.09
    ements
    0.09
    åĽŀäºĭ
    0.09
    anoia
    0.09
    Activations Density 0.035%

    No Known Activations