© 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. 39797
    Prev
    Next
    INDEX
    Explanations

    reading article or story

    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
    è®´
    -0.09
    .Private
    -0.09
    å¼ĢæĪ·
    -0.09
    stre
    -0.08
    HIR
    -0.08
     اÙĦعÙħر
    -0.08
     Protector
    -0.08
    éģ£
    -0.08
    è·¯æ¼Ķ
    -0.08
    è´§
    -0.08
    POSITIVE LOGITS
    çĮĽ
    0.12
    åī©ä½Ļ
    0.09
     Yates
    0.09
    lass
    0.08
    庶
    0.08
    åŁ
    0.08
    è¿ŀéĶģ
    0.08
    çļĭ
    0.08
    hta
    0.08
    emain
    0.08
    Activations Density 0.017%

    No Known Activations