© 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. 30403
    Prev
    Next
    INDEX
    Explanations

    minerals and ore deposits

    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
     апп
    -0.09
    Õ©
    -0.09
    Peripheral
    -0.09
    avors
    -0.09
    è¿ĩ大
    -0.08
     nạn
    -0.08
    æģIJæĢĸ
    -0.08
    éĢĥ
    -0.08
    å¤ĸåĽ´
    -0.08
    继
    -0.08
    POSITIVE LOGITS
     minerals
    0.12
    çŁ¿
    0.10
     miner
    0.09
     Minerals
    0.09
    éĩįæķ´
    0.09
    åįģæľĪ
    0.09
    第äºĮç§į
    0.09
    å²©çŁ³
    0.09
    åĨ³å¿ĥ
    0.08
     known
    0.08
    Activations Density 0.075%

    No Known Activations