© 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. 53371
    Prev
    Next
    INDEX
    Explanations

    carrying, bearing, supporting

    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
    jin
    -0.10
    æĭĺ
    -0.10
    renc
    -0.09
    .setParameter
    -0.08
    åģļæĪIJ
    -0.08
     mast
    -0.08
    è¿Ļä¸ĢçĤ¹
    -0.08
     Stan
    -0.08
    sWith
    -0.08
     Vict
    -0.08
    POSITIVE LOGITS
    æī¿è½½
    0.12
    è½½
    0.12
    è¼ī
    0.11
    è½½ä½ĵ
    0.11
    bear
    0.11
    éĴ¥åĮĻ
    0.10
     Äijá»±ng
    0.10
    çĨĬ
    0.10
    è²Ĭ
    0.10
     alo
    0.09
    Activations Density 0.063%

    No Known Activations