© 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. 22260
    Prev
    Next
    INDEX
    Explanations

    in many contexts, including people, sports, careers, and achievements

    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
    èĩ¾
    -0.11
    iju
    -0.10
    iness
    -0.10
    ban
    -0.09
    ince
    -0.09
    teen
    -0.09
    ton
    -0.09
    uset
    -0.09
    æĻĹ
    -0.09
    jÄħ
    -0.09
    POSITIVE LOGITS
    estic
    0.11
    stration
    0.11
    ä¸įäºĨ
    0.10
    lä
    0.10
    åĪ©çī©
    0.09
    éľīç´ł
    0.09
    ãĥ³ãĤ°
    0.09
    ement
    0.09
    eer
    0.09
    ç°ĩ
    0.09
    Activations Density 0.009%

    No Known Activations