© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 35605
    Prev
    Next
    INDEX
    Explanations

    sealing or closing components

    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
    æ·±åĪ»çļĦ
    -0.10
    è¿ĺä¸įå¤Ł
    -0.10
    æĭĸ
    -0.10
    åĪĨãģij
    -0.09
    è¿Ļæł·ä¸Ģ
    -0.09
    设计çIJĨ念
    -0.09
    éŁ¿
    -0.09
    æĸ°ä¸ĸ纪
    -0.09
    Nom
    -0.08
    IMO
    -0.08
    POSITIVE LOGITS
    å°ģ
    0.13
    çĽĸ
    0.11
    å¯Ĩå°ģ
    0.11
     sealing
    0.10
     sealed
    0.10
     Bless
    0.09
    habi
    0.09
    heck
    0.09
    ette
    0.09
    èĵĭ
    0.09
    Activations Density 0.113%

    No Known Activations