© 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. 57354
    Prev
    Next
    INDEX
    Explanations

    headquarters

    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
    uddy
    -0.10
    OBJ
    -0.09
    ADI
    -0.09
    çĦ¶
    -0.09
    -0.09
    covered
    -0.09
    Åij
    -0.08
    ifier
    -0.08
    zac
    -0.08
    äºĨä¸Ģ
    -0.08
    POSITIVE LOGITS
    pir
    0.11
    大楼
    0.09
    åĴĮ个人
    0.09
    æīĢåľ¨åľ°
    0.09
    ds
    0.09
    plex
    0.09
    å¨ĺ
    0.09
    æĸ°ä¸Ģè½®
    0.09
    éĩĮçļĦ
    0.08
     rond
    0.08
    Activations Density 0.012%

    No Known Activations