© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36644
    Prev
    Next
    INDEX
    Explanations

    lord followed by name or title

    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
    ook
    -0.10
    庶
    -0.09
    TING
    -0.09
    大å¥ĸ
    -0.09
     Jeb
    -0.09
    侬
    -0.09
    åĽĬ
    -0.08
    åĭĥåĭĥ
    -0.08
    ting
    -0.08
    sembling
    -0.08
    POSITIVE LOGITS
    ships
    0.15
    ship
    0.13
    sWith
    0.13
    inals
    0.11
    iales
    0.10
    ãĤ¥
    0.10
    ÑģÑĤво
    0.09
    enance
    0.09
    åĶ®ç¥¨
    0.09
    ndon
    0.09
    Activations Density 0.018%

    No Known Activations