© 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. 22330
    Prev
    Next
    INDEX
    Explanations

    All-Star game or contest

    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
    çĶ¨æ°´
    -0.10
    èĢģé¾Ħ
    -0.09
    ä¸įåĪ©
    -0.08
    å®ł
    -0.08
    embr
    -0.08
    enet
    -0.08
    eds
    -0.08
    azen
    -0.08
    éĹ²ç½®
    -0.08
    BT
    -0.08
    POSITIVE LOGITS
    agal
    0.10
    addtogroup
    0.09
    âĺħâĺħ
    0.09
    æĮ¡
    0.09
    Gap
    0.09
    POOL
    0.09
     Rocks
    0.09
    .FileSystem
    0.09
     Gap
    0.09
    ä¼ij
    0.09
    Activations Density 0.161%

    No Known Activations