© 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. 16862
    Prev
    Next
    INDEX
    Explanations

    packaging or packaged items

    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
    ÅĽmy
    -0.10
    å°»
    -0.10
    ships
    -0.10
    踪
    -0.09
    annies
    -0.09
    .itemView
    -0.09
    aines
    -0.08
    ì¹Ń
    -0.08
     thú
    -0.08
    beck
    -0.08
    POSITIVE LOGITS
    cing
    0.11
    çĶ©
    0.09
    ä¸ĬçļĦ
    0.09
    lı
    0.08
    ر
    0.08
    ri
    0.08
    dating
    0.08
    ä½ĵ系建设
    0.08
    teenth
    0.08
    p
    0.08
    Activations Density 0.013%

    No Known Activations