© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20907
    Prev
    Next
    INDEX
    Explanations

    fat, cholesterol, and health

    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
    åĨľæ°ijå·¥
    -0.09
    é¦ĸåħĪè¦ģ
    -0.09
    ildo
    -0.09
    .angular
    -0.09
     Gab
    -0.09
    çŀij
    -0.08
    ndx
    -0.08
    íķij
    -0.08
    æ²īé»ĺ
    -0.08
    catch
    -0.08
    POSITIVE LOGITS
     cholesterol
    0.11
    èĥĨåĽºéĨĩ
    0.11
    åIJ¸
    0.09
    è¡ĢèĦĤ
    0.09
    åİī
    0.09
    alie
    0.09
    åĪ³
    0.09
    è¶ħæłĩ
    0.09
    èĴº
    0.09
    åĹĵ
    0.09
    Activations Density 0.123%

    No Known Activations