© 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. 48812
    Prev
    Next
    INDEX
    Explanations

    printing, ink, and images

    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
    PLY
    -0.10
    aran
    -0.09
    éĢ¸
    -0.09
    atre
    -0.09
     whistle
    -0.09
    ôn
    -0.09
    鸿
    -0.09
    lia
    -0.08
    semblies
    -0.08
    è¾½
    -0.08
    POSITIVE LOGITS
    åį°èĬ±
    0.13
    åį¦
    0.09
     ink
    0.09
    åį°ç«ł
    0.09
    iana
    0.09
     пеÑĩ
    0.09
     printing
    0.08
    纪
    0.08
    quil
    0.08
    æŁĵ
    0.08
    Activations Density 0.163%

    No Known Activations