© 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. 4584
    Prev
    Next
    INDEX
    Explanations

    website links and URLs

    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
    åľ¨ä»ĸçļĦ
    -0.10
    æĺ¯æĪijçļĦ
    -0.09
    ãģĤãĤĭ
    -0.09
    åĢij
    -0.08
    çļĦ缮åħī
    -0.08
    åľ¨çİ°åľº
    -0.08
    家éŨåı£
    -0.08
    æĺ¯ä½ł
    -0.08
    æĺ¯åĽłä¸º
    -0.08
    orsi
    -0.08
    POSITIVE LOGITS
    æŁIJäºĽ
    0.09
    çī¹æ®ĬæĥħåĨµ
    0.09
    ALLY
    0.09
    åIJĪãĤıãģĽ
    0.08
    èĸ®
    0.08
    åħ¶å®ĥ
    0.08
    머
    0.08
    åIJĽåŃIJ
    0.08
    /or
    0.08
    oner
    0.08
    Activations Density 0.289%

    No Known Activations