© 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. 58715
    Prev
    Next
    INDEX
    Explanations

    in the process/midst/running/area/world/right/office

    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
    _forum
    -0.09
    å«ģ
    -0.09
     Word
    -0.09
    æĪIJ绩åįķ
    -0.08
    Warnings
    -0.08
    èĸ¯
    -0.08
    ä¸Ńéĥ¨
    -0.08
    人åĿĩ
    -0.08
    å¹³åİŁ
    -0.08
    evil
    -0.08
    POSITIVE LOGITS
    夹
    0.09
     thro
    0.09
    itori
    0.09
    çĶ¨å¾®ä¿¡
    0.08
     favor
    0.08
    èıĬ
    0.08
    \xc
    0.08
    æī©å®¹
    0.08
    ARAM
    0.08
    è±ģ
    0.08
    Activations Density 0.057%

    No Known Activations