© 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. 18492
    Prev
    Next
    INDEX
    Explanations

    asked me to

    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
    åİŁ
    -0.10
    lig
    -0.09
    igar
    -0.09
    èĥ½ä½¿
    -0.08
    ä¼ļ让
    -0.08
    ä¸įåĪĨ
    -0.08
    먹
    -0.08
    使人
    -0.08
    .postMessage
    -0.08
    çļĦä½ľçĶ¨
    -0.08
    POSITIVE LOGITS
    好好
    0.11
    赶快
    0.10
    èµĪ
    0.10
    æĬĵç´§
    0.10
    çİĸ
    0.09
    èµĸ以çĶŁåŃĺ
    0.09
    éĥı
    0.09
    æĻ¦
    0.09
    çķĻä¸ĭæĿ¥
    0.09
    赶紧
    0.09
    Activations Density 0.029%

    No Known Activations