© 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. 9943
    Prev
    Next
    INDEX
    Explanations

    formed in 1977 as a merger

    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
    elle
    -0.10
    Tur
    -0.10
    æ¦Ľ
    -0.09
    çĩİ
    -0.09
    orp
    -0.09
    被è¯Ħ为
    -0.08
    alsa
    -0.08
    etti
    -0.08
    线索
    -0.08
    身影
    -0.08
    POSITIVE LOGITS
    åĶ±
    0.09
    æł·åŃIJ
    0.08
    åĨ³æĪĺ
    0.08
    è¾Ī
    0.08
    ä¸įæĥľ
    0.08
    黥
    0.08
    èµĦæºIJåħ±äº«
    0.08
    çļĦæł·åŃIJ
    0.08
    spd
    0.08
    ibo
    0.08
    Activations Density 0.042%

    No Known Activations