© 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. 17144
    Prev
    Next
    INDEX
    Explanations

    agency or agencies

    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
    ened
    -0.12
    sWith
    -0.11
    ening
    -0.09
    å°¼äºļ
    -0.09
    ners
    -0.09
    æł·çļĦ
    -0.09
    ly
    -0.09
    ensions
    -0.09
    scribe
    -0.09
    åĬ¨æľº
    -0.09
    POSITIVE LOGITS
    稷
    0.10
    æ»ĵ
    0.10
    onne
    0.10
    forth
    0.10
    wide
    0.10
    phalt
    0.10
    gies
    0.09
    ester
    0.09
    ged
    0.09
    arat
    0.09
    Activations Density 0.019%

    No Known Activations