© 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. 20785
    Prev
    Next
    INDEX
    Explanations

    Saint Vincent and the Grenadines

    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
    çĽĺçĤ¹
    -0.09
    åĿª
    -0.09
    ä¸įå®ļ
    -0.08
    ä¹İ
    -0.08
    ä¸įä¸Ĭ
    -0.08
    è¾ĸ
    -0.08
    kee
    -0.08
    æ±ĩ
    -0.08
    åij¨è½¬
    -0.08
    åĽĽæĸ¹
    -0.08
    POSITIVE LOGITS
    ity
    0.10
    osite
    0.09
    è¿«
    0.09
    ãĥ£
    0.09
    itis
    0.08
    éĺ²çģ«
    0.08
    æ·Ģç²ī
    0.08
    æĻŀ
    0.08
    oute
    0.08
    é«ĺå±±
    0.08
    Activations Density 0.003%

    No Known Activations