© 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. 4372
    Prev
    Next
    INDEX
    Explanations

    scandal or controversy

    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
    碰åĪ°
    -0.10
    æ¹ĵ
    -0.10
    æľºæ¢°è®¾å¤ĩ
    -0.10
    vrier
    -0.09
    æĭ¾
    -0.09
    uais
    -0.09
    æīĴ
    -0.09
    .toolbox
    -0.09
    ç§ijæĬĢ
    -0.09
    åķ¤
    -0.09
    POSITIVE LOGITS
     case
    0.09
    导èĩ´
    0.09
    çīµ
    0.09
    åĬ©éķ¿
    0.08
    åıĭè°Ĭ
    0.08
     cumulative
    0.08
     Blob
    0.08
    äºļè¿IJ
    0.08
    éĶŁ
    0.08
    ago
    0.08
    Activations Density 0.302%

    No Known Activations