© 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. 19496
    Prev
    Next
    INDEX
    Explanations

    Tags: and related classifiers

    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
     tide
    -0.09
    ãģĦãĤī
    -0.08
    4
    -0.08
    isser
    -0.08
     veto
    -0.08
    .png
    -0.08
    6
    -0.08
     Fisheries
    -0.08
     mint
    -0.08
    9
    -0.08
    POSITIVE LOGITS
    åĩºåħ¥
    0.09
    èĸĦå¼±
    0.09
    éľĩèį¡
    0.09
    åľ¨æĦı
    0.09
    dek
    0.09
    _fa
    0.08
    çĦ¶åIJİåĨį
    0.08
    éĵ§
    0.08
    .*,
    0.08
    工夫
    0.08
    Activations Density 0.282%

    No Known Activations