© 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. 23272
    Prev
    Next
    INDEX
    Explanations

    origin or previous state

    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
    åĽ½åĨħå¤ĸ
    -0.09
    读æĩĤ
    -0.09
    æĮĤåľ¨
    -0.09
    æIJľ
    -0.08
    åıłåĬł
    -0.08
    æľīæĽ´å¥½çļĦ
    -0.08
     elder
    -0.08
    Executable
    -0.08
    ieri
    -0.08
    ziel
    -0.08
    POSITIVE LOGITS
    åİŁæĿ¥
    0.19
    å½ĵåĪĿ
    0.19
     originally
    0.18
    åİŁåħĪ
    0.17
    åİŁ
    0.17
     original
    0.17
    åİŁä¾Ĩ
    0.17
    åİŁæĿ¥çļĦ
    0.17
    åħĪåīį
    0.15
    æľĢåĪĿ
    0.15
    Activations Density 0.132%

    No Known Activations