© 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. 29428
    Prev
    Next
    INDEX
    Explanations

    words starting with f

    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
    son
    -0.10
    åįģä¸ĩ
    -0.09
    neath
    -0.08
    导åIJij
    -0.08
    aly
    -0.08
    ÑĤиÑĢов
    -0.08
     astore
    -0.08
     strengths
    -0.08
     adress
    -0.08
    empre
    -0.08
    POSITIVE LOGITS
    nof
    0.10
    /f
    0.10
    (fid
    0.09
    æĬ½åĩº
    0.09
    -f
    0.09
    rant
    0.09
    quip
    0.09
    nod
    0.08
    xCE
    0.08
     zaj
    0.08
    Activations Density 0.047%

    No Known Activations