© 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. 11901
    Prev
    Next
    INDEX
    Explanations

    actuated valves, float-type steam traps

    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
    alon
    -0.11
    ä»»
    -0.09
    orent
    -0.09
    åįķ车
    -0.09
    eren
    -0.09
    Invariant
    -0.09
    ç»ĨåĮĸ
    -0.09
    ุà¸ĩ
    -0.09
    iani
    -0.09
    horn
    -0.08
    POSITIVE LOGITS
    ÑĤик
    0.09
    å¿ĥæĢģ
    0.09
     Gardner
    0.09
    ä¿Ŀå®ī
    0.08
    สาร
    0.08
    -pr
    0.08
     Ramp
    0.08
     gard
    0.08
    åĿĩæľī
    0.08
    ais
    0.08
    Activations Density 0.263%

    No Known Activations