© 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. 36560
    Prev
    Next
    INDEX
    Explanations

    world's

    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
    aghan
    -0.09
     rainbow
    -0.09
    anza
    -0.08
     Arrival
    -0.08
    å¯ĨåĪĩ
    -0.08
    ç¥Ł
    -0.08
    -wow
    -0.08
    蹶
    -0.08
    èī°å·¨
    -0.08
     vans
    -0.08
    POSITIVE LOGITS
    uded
    0.10
    éħī
    0.10
    èĮĥåĽ´åĨħ
    0.09
    uset
    0.09
    /world
    0.09
    lier
    0.09
    è§ĩ
    0.09
    çĿĢä»ĸ
    0.09
    ENU
    0.09
    第ä¸Ģä½į
    0.09
    Activations Density 0.035%

    No Known Activations