© 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. 34759
    Prev
    Next
    INDEX
    Explanations

    appliances

    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
    -0.12
    isplay
    -0.11
     Phaser
    -0.10
    ignon
    -0.09
    ners
    -0.09
    ãģŀ
    -0.09
     иÑģп
    -0.09
    rooms
    -0.09
    llib
    -0.09
    liner
    -0.09
    POSITIVE LOGITS
     latter
    0.11
    holders
    0.11
    MENTS
    0.10
    HOLDER
    0.10
    åIJİèĢħ
    0.10
    æľīä¸Ģ次
    0.10
    åīįèĢħ
    0.09
    еÑħ
    0.09
    öst
    0.08
     incumb
    0.08
    Activations Density 0.012%

    No Known Activations