© 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. 47873
    Prev
    Next
    INDEX
    Explanations

    market research decision-making

    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
    åĩĮ
    -0.09
    趸
    -0.08
    åıī
    -0.08
    çİĦ
    -0.08
     instance
    -0.08
    åIJŀ
    -0.08
    è°Ī
    -0.07
    çħ¤
    -0.07
     gre
    -0.07
    vet
    -0.07
    POSITIVE LOGITS
    SUMER
    0.11
     bowl
    0.11
    æ´ŀå¯Ł
    0.10
    éĢĨ
    0.10
    .ordinal
    0.10
    éŀł
    0.10
    brook
    0.10
     Bowl
    0.09
    Bow
    0.09
    çļĵ
    0.09
    Activations Density 0.072%

    No Known Activations