© 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. 2802
    Prev
    Next
    INDEX
    Explanations

    background in context

    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
    anh
    -0.10
    åı¯æĥľ
    -0.09
    бо
    -0.09
    idor
    -0.09
    uh
    -0.09
    /her
    -0.08
    è¿ĩçļĦ
    -0.08
    anny
    -0.08
    uga
    -0.08
    Ŀå§ĭ
    -0.08
    POSITIVE LOGITS
    sWith
    0.09
    alsa
    0.09
    人士
    0.09
    -mounted
    0.09
    å·¥ä½ľèĢħ
    0.08
    ood
    0.08
    mé
    0.08
    à¹Ģà¸Ĥา
    0.08
    ãģĩ
    0.08
    kre
    0.08
    Activations Density 0.028%

    No Known Activations