© 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. 26712
    Prev
    Next
    INDEX
    Explanations

    consequence connector

    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
    ä½Ĩå®ĥ
    -0.10
    èĢĮä¸Ķè¿ĺ
    -0.10
    amas
    -0.09
    åĩĮ
    -0.09
    æĮ½
    -0.09
    å¬ĸ
    -0.09
    åIJĮæŶè¿ĺ
    -0.09
    大桥
    -0.09
    èĿĩ
    -0.09
    åѦåijĺ
    -0.09
    POSITIVE LOGITS
    forth
    0.10
    /or
    0.08
    ensch
    0.08
    ä¹Łå°±
    0.07
     å
    0.07
    æīĢéľĢè¦ģçļĦ
    0.07
    çĶŁæ´»è´¨éĩı
    0.07
     Pep
    0.07
    wa
    0.07
    geh
    0.07
    Activations Density 0.091%

    No Known Activations