© 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. 55057
    Prev
    Next
    INDEX
    Explanations

    Bernard names and endings

    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
    igg
    -0.13
    ided
    -0.10
    éĩįè¦ģæĦıä¹ī
    -0.10
    æĥħåĨµä¸ĭ
    -0.10
    -ever
    -0.09
    å¾Ĺä½ı
    -0.09
    teenth
    -0.09
    ãĤĪãģĨãģ«ãģªãģ£ãģŁ
    -0.09
    .Directory
    -0.09
    ë°Ģ
    -0.09
    POSITIVE LOGITS
    éĺĹ
    0.10
    ards
    0.10
    rica
    0.09
    elli
    0.09
    Ñĩик
    0.09
    _ADAPTER
    0.08
    ores
    0.08
    ists
    0.08
    天é¹ħ
    0.08
    и
    0.08
    Activations Density 0.018%

    No Known Activations