© 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. 23450
    Prev
    Next
    INDEX
    Explanations

    choice or choice experiment

    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
    çĦ°
    -0.11
    容纳
    -0.11
    izzy
    -0.11
    éĢļè¡Į
    -0.10
    èµĸ以çĶŁåŃĺ
    -0.10
    ãģĹãĤĩãģĨ
    -0.09
    è°£
    -0.09
    转载
    -0.09
    ä¸įå°½
    -0.09
     reproduction
    -0.09
    POSITIVE LOGITS
     Defaults
    0.10
    Defaults
    0.10
     nud
    0.10
    é¢Ĩ
    0.09
    è·Ĺ
    0.09
    hic
    0.09
    Default
    0.09
    ÙĤÙĩ
    0.09
    水墨
    0.09
     bl
    0.09
    Activations Density 0.139%

    No Known Activations