© 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. 9801
    Prev
    Next
    INDEX
    Explanations

    Baker or baker

    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
    ouncy
    -0.09
    sing
    -0.08
    ible
    -0.08
    жен
    -0.08
     tái
    -0.08
    orent
    -0.08
    inne
    -0.08
    encial
    -0.08
    IPS
    -0.08
    Äįe
    -0.08
    POSITIVE LOGITS
    éļıæŶéļıåľ°
    0.11
    èģĶåIJĪä¼ļ
    0.10
    ruptcy
    0.10
    ë§ī
    0.10
    æŀķ
    0.09
    hurst
    0.09
    å°ı康社ä¼ļ
    0.09
    marked
    0.09
    åĪ¶åĵģ
    0.09
    atable
    0.09
    Activations Density 0.008%

    No Known Activations