© 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. 32526
    Prev
    Next
    INDEX
    Explanations

    medical and hospital transport

    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
    好æľĭåıĭ
    -0.09
    ptype
    -0.09
    éļľ
    -0.09
    åıĤä¸İèĢħ
    -0.09
    -flat
    -0.09
    åIJ¬è¯¾
    -0.08
    inspace
    -0.08
     FUN
    -0.08
     Tight
    -0.08
    驼
    -0.08
    POSITIVE LOGITS
    延误
    0.12
    èĢ½
    0.10
    åĪ°åľº
    0.10
    arriv
    0.10
    éĹ®éģĵ
    0.10
    è¿ĽéŨ
    0.09
     dagger
    0.09
     arrival
    0.09
    绿èī²éĢļéģĵ
    0.09
     arrivals
    0.09
    Activations Density 0.192%

    No Known Activations