© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21240
    Prev
    Next
    INDEX
    Explanations

    start working

    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
     пÑĢож
    -0.10
    车ä½į
    -0.09
    èŀŁ
    -0.09
    æľ
    -0.09
    æľīåĬ©
    -0.08
    æIJŀ好
    -0.08
    ers
    -0.08
    æŃ£å¸¸ä½¿çĶ¨
    -0.08
    æ·¡åĮĸ
    -0.08
     dis
    -0.08
    POSITIVE LOGITS
    ATUS
    0.11
    ä¸ŃæĸŃ
    0.11
    æ¯ħçĦ¶
    0.11
    追æ±Ĥ
    0.10
    追寻
    0.10
    åĽŀå½Ĵ
    0.10
    bsp
    0.10
    转åIJij
    0.10
    éĩįå¿ĥ
    0.10
    æĬķ身
    0.10
    Activations Density 0.094%

    No Known Activations