© 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. 59150
    Prev
    Next
    INDEX
    Explanations

    loved or beloved things

    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
    ä¸į对
    -0.09
    acy
    -0.08
     Exped
    -0.08
    社ä¼ļåĮĸ
    -0.08
    hdl
    -0.08
    cy
    -0.08
    hua
    -0.08
    _asc
    -0.08
     bé
    -0.08
    .dense
    -0.08
    POSITIVE LOGITS
    inki
    0.10
    anske
    0.10
    .startTime
    0.09
    秩
    0.09
    hani
    0.09
     patt
    0.09
    å·²ä¹ħçļĦ
    0.09
    ìĤ¬íķŃ
    0.09
    ensibly
    0.09
    olec
    0.09
    Activations Density 0.053%

    No Known Activations