© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 17517
    Prev
    Next
    INDEX
    Explanations

    adding sequences

    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
    æīĢ以æĪij们
    -0.10
    æīĢ以æĪij
    -0.08
    arta
    -0.08
    ãģ¾ãĤĮ
    -0.08
    cles
    -0.08
    åľ¨æĪij
    -0.08
    èĥĻ
    -0.08
    æĪijèĩªå·±
    -0.08
    zens
    -0.08
    /generated
    -0.08
    POSITIVE LOGITS
    è¿ĽèĢĮ
    0.14
    以åıĬ
    0.12
    éĩįçĤ¹åħ³æ³¨
    0.12
    ä»İèĢĮ
    0.11
    åħ¶ä¸ŃåĮħæĭ¬
    0.10
    åIJĮæŶè¿ĺ
    0.10
    éĩįçĤ¹
    0.10
    并éĢļè¿ĩ
    0.10
    åĮħæĭ¬
    0.10
     serta
    0.10
    Activations Density 0.290%

    No Known Activations