© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 48991
    Prev
    Next
    INDEX
    Explanations

    names and company suffixes

    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
    龸
    -0.09
    ä¸¤åĽ½
    -0.08
    éħ¿
    -0.08
    æĦıå¤ĸ
    -0.08
    Stamped
    -0.08
     ford
    -0.08
    çĸĨ
    -0.08
    cke
    -0.08
     Ford
    -0.08
     Getty
    -0.08
    POSITIVE LOGITS
    è´µ
    0.10
    çijĽ
    0.10
     Din
    0.10
    åħ¸
    0.10
    upt
    0.09
    çIJĨ解åĴĮ
    0.09
    礼
    0.09
    amat
    0.09
    èĥĸ
    0.09
    ç½ijåºĹ
    0.09
    Activations Density 0.039%

    No Known Activations