© 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. 24319
    Prev
    Next
    INDEX
    Explanations

    parental caregiving

    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
    ogue
    -0.12
    çĮİ
    -0.10
     Woo
    -0.10
    åIJ¬å®Į
    -0.09
    .CV
    -0.09
    åĭĭ
    -0.08
    èī²æ³½
    -0.08
    乡
    -0.08
     grown
    -0.08
    ä¸įæĺĵ
    -0.08
    POSITIVE LOGITS
     Loft
    0.10
    å±İ
    0.09
    exclusive
    0.09
    ä¸Ńè¶ħ
    0.09
     Exclusive
    0.09
    ä¸ĵåįĸ
    0.09
     dedication
    0.09
    Exclusive
    0.08
     discharged
    0.08
    çĻ¾ç§ij
    0.08
    Activations Density 0.085%

    No Known Activations