© 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. 18538
    Prev
    Next
    INDEX
    Explanations

    pros and cons

    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
    год
    -0.10
    第ä¸Ģæī¹
    -0.09
     Kro
    -0.09
    æĭ³
    -0.09
    ä¹łæĥ¯
    -0.08
    hip
    -0.08
    åĨł
    -0.08
    ople
    -0.08
    æIJĶ
    -0.08
    .predicate
    -0.08
    POSITIVE LOGITS
     Pros
    0.11
    ãĥ¡ãĥªãĥĥãĥĪ
    0.10
    Pros
    0.09
    èĽ
    0.09
     pros
    0.09
    åĽĽå¤Ħ
    0.09
    窨
    0.09
    æĻ®åıĬ
    0.09
    æĹ©çĤ¹
    0.08
    ç§ijæĬĢ大åѦ
    0.08
    Activations Density 0.042%

    No Known Activations