© 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. 24277
    Prev
    Next
    INDEX
    Explanations

    what do or does

    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
    BorderStyle
    -0.10
    åIJ¬çĿĢ
    -0.10
    å»ĵ
    -0.09
    onom
    -0.09
    äºĮèĥİ
    -0.09
    .US
    -0.08
    ãģĵãģ¡ãĤī
    -0.08
    ä¸Ģ大æĹ©
    -0.08
    èij«èĬ¦
    -0.08
    è¹Ģ
    -0.08
    POSITIVE LOGITS
    UAL
    0.08
    笳
    0.08
    _SAMPL
    0.08
     Liber
    0.08
    icina
    0.08
    Pitch
    0.08
    머
    0.08
     Depart
    0.08
    Ñıд
    0.08
    çĸµ
    0.08
    Activations Density 0.015%

    No Known Activations