© 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. 20457
    Prev
    Next
    INDEX
    Explanations

    smh abbreviation

    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
    è¡Ĺ
    -0.09
    ä¸į该
    -0.09
    忧
    -0.09
    æİł
    -0.09
    åĭ¿
    -0.08
    è¼Ŀ
    -0.08
    åı¬éĽĨ
    -0.08
     Micha
    -0.08
    обÑĢаз
    -0.08
    flare
    -0.08
    POSITIVE LOGITS
    å®ħ
    0.11
    å²Ľä¸Ĭ
    0.10
    åĬĪ
    0.10
     Zelda
    0.09
    éĹ°
    0.09
    诹
    0.09
    éĢĤ度
    0.08
    éĵĬ
    0.08
     Ned
    0.08
    绪
    0.08
    Activations Density 0.046%

    No Known Activations