© 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. 32080
    Prev
    Next
    INDEX
    Explanations

    involved in communities

    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
    çĪ±ç¾İ
    -0.10
    åīij
    -0.09
    éĿłçĿĢ
    -0.09
    çĶŁçIJĨ
    -0.08
     Flash
    -0.08
    åĬį
    -0.08
    ike
    -0.08
    æľµ
    -0.08
     Beste
    -0.08
    .bi
    -0.08
    POSITIVE LOGITS
    积æŀģåıĤä¸İ
    0.14
    åıĤä¸İ
    0.14
    è´¡çĮ®
    0.13
    å¥īçĮ®
    0.13
     involvement
    0.13
    åıĤåĬł
    0.12
    åħ¬çĽĬæ´»åĬ¨
    0.12
    /community
    0.12
    åıĥèĪĩ
    0.11
    ä»ĺåĩº
    0.11
    Activations Density 0.134%

    No Known Activations