© 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. 9971
    Prev
    Next
    INDEX
    Explanations

    WARRANTIES OR CONDITIONS

    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
    å¿«
    -0.09
    sh
    -0.09
    sec
    -0.09
    æķħ乡
    -0.09
    æĮīè§Ħå®ļ
    -0.08
    aira
    -0.08
    æĽĿ
    -0.08
    quest
    -0.08
    éĶIJ
    -0.08
    éĩijåįİ
    -0.08
    POSITIVE LOGITS
    æľīä»»ä½ķ
    0.10
     IMPLIED
    0.10
    URRE
    0.10
    æ¯ı次éĥ½
    0.09
    å¿ĺ
    0.09
    ä¸Ŀ毫
    0.09
    avery
    0.09
    antom
    0.09
    ä»Ģä¹Īäºĭ
    0.09
    为éĩįçĤ¹
    0.09
    Activations Density 0.065%

    No Known Activations