© 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. 7057
    Prev
    Next
    INDEX
    Explanations

    specialized care and attention

    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
    æī¿æĭħ
    -0.09
    burgh
    -0.08
     Maj
    -0.08
    haar
    -0.08
    ve
    -0.08
    foto
    -0.08
     vaguely
    -0.08
    assin
    -0.08
    .addListener
    -0.07
     Territory
    -0.07
    POSITIVE LOGITS
    ç»Ĩå¿ĥ
    0.13
    ç»Ĩèĩ´
    0.13
    å¯ĨéĽĨ
    0.13
     вним
    0.12
    ä¸ĵ人
    0.12
    æĤī
    0.12
     внимание
    0.12
    ç²¾å¿ĥ
    0.12
     care
    0.11
    ä½ĵè´´
    0.11
    Activations Density 0.050%

    No Known Activations