© 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. 26370
    Prev
    Next
    INDEX
    Explanations

    them all

    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
    å®ĥçļĦ
    -0.11
    -minded
    -0.10
    åħ¶ä½Ļ
    -0.09
    es
    -0.09
     remainder
    -0.09
     itself
    -0.09
    åħ¶
    -0.09
    ÙĨا
    -0.09
     its
    -0.09
    ãģĿãĤĮãģ«
    -0.09
    POSITIVE LOGITS
    atically
    0.18
    /her
    0.15
    elves
    0.14
    soever
    0.14
    ming
    0.12
    perature
    0.12
    self
    0.11
    usic
    0.11
    atics
    0.11
    orrow
    0.11
    Activations Density 0.061%

    No Known Activations