© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 6808
    Prev
    Next
    INDEX
    Explanations

    help sections or files

    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
    æ®ĩ
    -0.10
    åıĮèµ¢
    -0.09
    AGER
    -0.09
    aug
    -0.09
    ä¾ĽéĶĢ
    -0.08
     compliments
    -0.08
    ç²®é£Ł
    -0.08
    涨价
    -0.08
     Blanc
    -0.08
    没æľīä»Ģä¹Ī
    -0.08
    POSITIVE LOGITS
     ÑģпÑĢав
    0.11
    desk
    0.11
    æ±ĤåĬ©
    0.10
    abr
    0.09
     about
    0.09
    /about
    0.09
    åıĭ好
    0.09
    èĭĽ
    0.09
    åŁºéĩijä¼ļ
    0.09
     бÑİ
    0.08
    Activations Density 0.214%

    No Known Activations