© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 8071
    Prev
    Next
    INDEX
    Explanations

    subfamily or family classifications

    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
    è°ı
    -0.11
    èĢģåħµ
    -0.09
    èµ·æĿ¥
    -0.09
    vod
    -0.09
    åΤ
    -0.09
     bag
    -0.09
    彦
    -0.08
    åĩij
    -0.08
    æľį
    -0.08
    饰
    -0.08
    POSITIVE LOGITS
    ersive
    0.10
    ä½İ头
    0.10
    éļ¶å±ŀäºİ
    0.09
     extrad
    0.09
    计éĩı
    0.08
    Ln
    0.08
     Plan
    0.08
    iston
    0.08
     Upper
    0.08
    =min
    0.08
    Activations Density 0.074%

    No Known Activations