© 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. 7804
    Prev
    Next
    INDEX
    Explanations

    highest level or rank

    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
    ivery
    -0.10
     пÑĢеж
    -0.09
    åŁİåł¡
    -0.09
    allet
    -0.09
    åĶĩ
    -0.08
    Transformer
    -0.08
     Lust
    -0.08
     Ult
    -0.08
    .bin
    -0.08
     Publi
    -0.08
    POSITIVE LOGITS
    é«ĺå±Ĥ
    0.16
    å±Ĥ级
    0.14
    éĺ¶å±Ĥ
    0.12
    å±Ĥ次
    0.12
    å±Ĥ
    0.12
    åIJĦ级
    0.12
     level
    0.12
    级åĪ«çļĦ
    0.12
     cấp
    0.12
    å±ĤéĿ¢
    0.12
    Activations Density 0.106%

    No Known Activations