© 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. 9260
    Prev
    Next
    INDEX
    Explanations

    club or group meetings

    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
    åį·
    -0.10
    ä¿¡æģ¯åĮĸ
    -0.09
    åĽŀå¤į
    -0.09
     mans
    -0.09
    çī¢
    -0.09
    çłĶ究æĪIJæŀľ
    -0.08
    _KP
    -0.08
    ãĥĹãĥª
    -0.08
    çļĩ
    -0.08
    IPH
    -0.08
    POSITIVE LOGITS
    ç¤¾åĽ¢
    0.17
     club
    0.16
    俱ä¹IJéĥ¨
    0.16
     CLUB
    0.15
    åįıä¼ļ
    0.14
     clubs
    0.14
    club
    0.13
     Club
    0.13
    å°ıç»Ħ
    0.12
    Club
    0.12
    Activations Density 0.188%

    No Known Activations