© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 2763
    Prev
    Next
    INDEX
    Explanations

    Cornwall and Devon

    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
    å¨ī
    -0.11
    éħĭ
    -0.09
    å¤Ķ
    -0.09
    ayed
    -0.09
    秧
    -0.09
    Äĥng
    -0.08
    æ®ĸ
    -0.08
    éķIJ
    -0.08
    çĶŁæ®ĸ
    -0.08
    西å®ī
    -0.08
    POSITIVE LOGITS
    iers
    0.09
    æĪijè¿ĺæĺ¯
    0.09
    ite
    0.08
    å¿įä¸įä½ı
    0.08
     beef
    0.08
    éĵ¤
    0.08
    .ObjectModel
    0.08
    rial
    0.08
    ters
    0.08
    tle
    0.08
    Activations Density 0.014%

    No Known Activations