© 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. 52235
    Prev
    Next
    INDEX
    Explanations

    scuba diving

    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
    æĿ¯
    -0.09
    rico
    -0.09
    å»ī
    -0.09
    å¤©åºľ
    -0.09
    ëĦIJ
    -0.08
     broad
    -0.08
    atform
    -0.08
    ãģ±
    -0.08
    ANO
    -0.08
     Laur
    -0.08
    POSITIVE LOGITS
    æīijåħĭ
    0.09
    åIJĮæľŁ
    0.09
    磶
    0.09
    fit
    0.08
     kep
    0.08
    avern
    0.08
    æ·¡åĮĸ
    0.08
    aska
    0.08
     tack
    0.08
    çĶ¨åĵģ
    0.08
    Activations Density 0.007%

    No Known Activations