© 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. 30456
    Prev
    Next
    INDEX
    Explanations

    COVID symptoms

    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
    èįī
    -0.10
    åĸĿäºĨ
    -0.09
    èĢķåľ°
    -0.09
    té
    -0.08
    å¤įåħ´
    -0.08
    æĸ°å¾ģç¨ĭ
    -0.08
    FolderPath
    -0.08
    è¿ĩå¾Ĺ
    -0.08
    è£ĺ
    -0.08
    çĵľ
    -0.08
    POSITIVE LOGITS
    éļĶ离
    0.13
    å±ħ家
    0.12
    éĺ²æݧ
    0.11
    éļĶçĿĢ
    0.10
    ç¡®è¯ĬçĹħä¾ĭ
    0.10
    çĹħæ¯Ĵ
    0.10
     quar
    0.10
    æģIJæħĮ
    0.09
     ventil
    0.09
    åľ¨å®¶
    0.09
    Activations Density 0.286%

    No Known Activations