© 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. 8412
    Prev
    Next
    INDEX
    Explanations

    small size

    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
    宽æķŀ
    -0.09
    åłĤ
    -0.09
    æħĪ
    -0.09
    宽éĺĶ
    -0.09
    zej
    -0.09
     Moderate
    -0.09
    çĴŁ
    -0.08
    ë§ĺ
    -0.08
    é£
    -0.08
    udio
    -0.08
    POSITIVE LOGITS
     tiny
    0.22
    è¿·ä½ł
    0.21
    å°ıå·§
    0.20
    å°ıåŀĭ
    0.20
     small
    0.20
    /tiny
    0.19
    tiny
    0.19
     smaller
    0.19
    å°ıå°ı
    0.19
    å¾®åŀĭ
    0.19
    Activations Density 0.297%

    No Known Activations