© 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. 23198
    Prev
    Next
    INDEX
    Explanations

    with words following

    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
    æīĢè°ĵ
    -0.11
     themselves
    -0.10
    çĶļèĩ³
    -0.10
    åĻİ
    -0.10
    èĢĮæĺ¯
    -0.10
    .basicConfig
    -0.10
    è¾Ī
    -0.10
    apore
    -0.09
    ILES
    -0.09
    æĪijèĩªå·±
    -0.09
    POSITIVE LOGITS
    使åħ¶
    0.10
    æĪIJ为ä¸ŃåĽ½
    0.10
    æĺ¯ä½ł
    0.10
    æĮīçħ§
    0.09
     normally
    0.09
     tháºŃt
    0.09
     appropriate
    0.09
     usual
    0.08
    大约
    0.08
    å°½åı¯èĥ½
    0.08
    Activations Density 0.135%

    No Known Activations