© 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. 24343
    Prev
    Next
    INDEX
    Explanations

    names starting with Ke

    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
    sWith
    -0.12
    eur
    -0.10
    åı¨
    -0.09
    åĨĮ
    -0.09
    æĬĹæĪĺ
    -0.09
    ioni
    -0.09
    UMENT
    -0.09
    gie
    -0.08
    service
    -0.08
    ação
    -0.08
    POSITIVE LOGITS
    åĭĥåĭĥ
    0.13
    ystone
    0.11
    å·²ä¹ħçļĦ
    0.10
    elight
    0.10
    enga
    0.10
    pler
    0.09
    paring
    0.09
    formance
    0.09
    eson
    0.09
    ufe
    0.08
    Activations Density 0.024%

    No Known Activations