© 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. 48859
    Prev
    Next
    INDEX
    Explanations

    hearing loss and anemia

    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
    åĩ¿
    -0.12
    æİĮ声
    -0.11
     Vish
    -0.10
    .Unique
    -0.09
    Visibility
    -0.09
    çļĦæĥħ绪
    -0.09
    екÑĤоÑĢ
    -0.09
    æīĭæİĮ
    -0.09
    éĵ¤
    -0.09
    .Visibility
    -0.09
    POSITIVE LOGITS
    è´«è¡Ģ
    0.12
    ç¨ĭ度
    0.10
    eya
    0.09
     proble
    0.09
    çĹĩ
    0.09
    缺
    0.08
    便ç§ĺ
    0.08
    éĹ®é¢ĺ
    0.08
     problems
    0.08
    CBC
    0.08
    Activations Density 0.653%

    No Known Activations