© 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. 51613
    Prev
    Next
    INDEX
    Explanations

    tag and tags

    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
     narr
    -0.09
    éĶ·
    -0.09
    çħ§
    -0.09
    íĥķ
    -0.09
    .annot
    -0.09
    (pdf
    -0.08
    çıŃ主任
    -0.08
    ÙĨعÙħ
    -0.08
     enlarg
    -0.08
    FXML
    -0.08
    POSITIVE LOGITS
    æłĩçŃ¾
    0.20
     tags
    0.18
     tag
    0.18
    Tags
    0.15
    -tags
    0.15
    .tags
    0.15
    Tag
    0.15
    /tag
    0.15
    (tags
    0.15
     Tags
    0.15
    Activations Density 0.090%

    No Known Activations