© 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. 36135
    Prev
    Next
    INDEX
    Explanations

    email addresses after "at"

    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
    pac
    -0.09
    æĩ¿
    -0.09
    人éĢī
    -0.09
    lam
    -0.09
    tron
    -0.09
    èĩ³äºİ
    -0.09
    æ³µ
    -0.09
    -Man
    -0.08
    rar
    -0.08
    å°±å¤Ł
    -0.08
    POSITIVE LOGITS
     ngh
    0.10
    éĢIJæŃ¥
    0.09
    éĢĤå½ĵ
    0.09
    -follow
    0.09
    åįģä¸īå±Ĭ
    0.09
    çĮĽçĦ¶
    0.08
    ç§Ģ丽
    0.08
    fü
    0.08
    åĸŁ
    0.08
    æľ«
    0.08
    Activations Density 0.013%

    No Known Activations