© 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. 1286
    Prev
    Next
    INDEX
    Explanations

    offers and suggestions

    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
    ASM
    -0.10
    纵åIJij
    -0.10
    åķĸ
    -0.09
    汶
    -0.09
     impuls
    -0.09
    nat
    -0.08
    è½²
    -0.08
    çĪ·
    -0.08
    ikal
    -0.08
    FUL
    -0.08
    POSITIVE LOGITS
     ideas
    0.12
     suggestions
    0.11
    æĦıè§ģåıįé¦Ī
    0.11
    ideas
    0.10
    Suggestions
    0.10
     Ideas
    0.10
    æĦıè§ģ
    0.10
    æĶ¶è´¹ç«Ļ
    0.09
    ç§ģ人
    0.09
    æĦıè§ģ建议
    0.09
    Activations Density 0.102%

    No Known Activations