© 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. 6090
    Prev
    Next
    INDEX
    Explanations

    father

    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
    ingly
    -0.13
     herself
    -0.11
    ä¸İåIJ¦
    -0.10
    æļ¹
    -0.10
    èĩªå®¶
    -0.10
    妯
    -0.10
    UG
    -0.09
    稷
    -0.09
    uje
    -0.09
    nist
    -0.09
    POSITIVE LOGITS
    baugh
    0.10
    sti
    0.09
    pan
    0.09
    媽媽
    0.09
     disob
    0.08
    BarItem
    0.08
    HIP
    0.08
    дол
    0.08
    MOST
    0.08
     зло
    0.08
    Activations Density 0.044%

    No Known Activations