© 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. 39212
    Prev
    Next
    INDEX
    Explanations

    guess what

    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
    .createFrom
    -0.10
    建æĪIJåIJİ
    -0.10
    äºĨä¸Ģåı¥
    -0.09
    空
    -0.08
    ساس
    -0.08
    ìĩĦ
    -0.08
    éħ£
    -0.08
    åŁºæľ¬ä¸Ĭéĥ½
    -0.08
     Sag
    -0.08
    IED
    -0.08
    POSITIVE LOGITS
    able
    0.12
    ably
    0.11
    æľīå¤ļå°ij
    0.10
    çĮľ
    0.09
    allee
    0.09
    ذا
    0.09
    ings
    0.09
    press
    0.09
    leaf
    0.08
    ãĤĤãģ£ãģ¨
    0.08
    Activations Density 0.003%

    No Known Activations