© 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. 2167
    Prev
    Next
    INDEX
    Explanations

    undertake initiatives

    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
    èIJ½åľ¨
    -0.09
    çĸij
    -0.09
     Scho
    -0.09
    ä¾Ľæ±Ĥ
    -0.08
    okin
    -0.08
    attention
    -0.08
     regards
    -0.08
    å±ĢéĻIJäºİ
    -0.08
    æŧ
    -0.08
    onom
    -0.08
    POSITIVE LOGITS
    社ä¼ļ责任
    0.10
    äºĨä¸Ģç³»åĪĹ
    0.10
     vign
    0.09
    åıªä¸º
    0.09
    æ¼Ĥæµģ
    0.09
     journeys
    0.09
    éĩįä»»
    0.09
     fark
    0.09
    çļĦæ¨¡æł·
    0.09
    .AspNet
    0.09
    Activations Density 0.014%

    No Known Activations