© 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. 7420
    Prev
    Next
    INDEX
    Explanations

    sea-level, canal, depth, flat, sorting

    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
     Mountain
    -0.13
    çĻ»å±±
    -0.12
    æĤ¬å´ĸ
    -0.11
    峡
    -0.10
    æ³īæ°´
    -0.10
    å±±èĦī
    -0.10
    nut
    -0.10
    Mountain
    -0.10
    mount
    -0.10
    å´Ĥ
    -0.09
    POSITIVE LOGITS
    éĺ¡
    0.12
    éĦļ
    0.11
    æ±´
    0.11
    åł¤
    0.10
    å£ŀ
    0.10
    èĵ¬
    0.10
    ä»İä¸ļ
    0.09
    顶
    0.09
     swamp
    0.09
    (off
    0.09
    Activations Density 0.140%

    No Known Activations