© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 59228
    Prev
    Next
    INDEX
    Explanations

    political regimes

    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
    Negative Logits
    combe
    -0.11
    ropri
    -0.10
    çĸĻ
    -0.09
    ä»Ģä¹ĪåİŁåĽł
    -0.09
    worth
    -0.09
    診
    -0.09
    常å§Ķ
    -0.09
    iffs
    -0.09
    man
    -0.08
    åĪ°è¿ĻéĩĮ
    -0.08
    POSITIVE LOGITS
    iro
    0.10
    amp
    0.10
    urally
    0.10
    atic
    0.09
    lement
    0.09
    efore
    0.09
    atics
    0.09
    кÑĢеп
    0.09
    iller
    0.09
    led
    0.08
    Activations Density 0.007%

    No Known Activations