© 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. 48762
    Prev
    Next
    INDEX
    Explanations

    epilepsy, language, poetic, losses, celebrates

    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
    èĬĻèĵī
    -0.09
    ä¹Ŀåįģ
    -0.09
    è´µ
    -0.08
     literally
    -0.08
    èĢĥèĻijåĪ°
    -0.08
    è¿Ľåĩº
    -0.08
    åIJĮæľŁ
    -0.08
    以èī²
    -0.08
    èĪįå¾Ĺ
    -0.08
     literal
    -0.08
    POSITIVE LOGITS
    ãĤĨ
    0.10
    对è¯Ŀ
    0.10
    åĪ¶çº¦
    0.10
    VERIFY
    0.09
    åįĥä¸ĩ
    0.09
    åIJijå¾Ģ
    0.09
    æŃ£ä¹ī
    0.09
    跨度
    0.09
    维度
    0.08
     Gul
    0.08
    Activations Density 0.210%

    No Known Activations