© 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. 30182
    Prev
    Next
    INDEX
    Explanations

    bluffing or ads

    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
    nte
    -0.10
    ä»Ĩ
    -0.09
    ece
    -0.09
    èįīæ¡Ī
    -0.09
    å½»
    -0.09
    سÙħ
    -0.09
    ä¹IJåĽ¢
    -0.09
    å°ıç»Ħ
    -0.09
    ngth
    -0.09
    ä¹ħäºĨ
    -0.09
    POSITIVE LOGITS
    åŃļ
    0.10
    å¾Ĥ
    0.09
    ware
    0.09
    ãģ£ãģ¨
    0.09
    éĽī
    0.09
    tures
    0.09
    èĦ¯
    0.09
    nier
    0.09
    é¸Ń
    0.08
    venir
    0.08
    Activations Density 0.002%

    No Known Activations