© 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. 31416
    Prev
    Next
    INDEX
    Explanations

    precise, precipitation, precedential

    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
    zed
    -0.10
    tered
    -0.10
    athan
    -0.09
    ered
    -0.09
    佬
    -0.09
    мел
    -0.09
    åŃIJéĩĮ
    -0.08
     nghá»ģ
    -0.08
    aways
    -0.08
    ç½ijçIJĥ
    -0.08
    POSITIVE LOGITS
    amber
    0.10
    ä»ĬçĶŁ
    0.10
    emente
    0.09
    onom
    0.09
    oes
    0.09
    avis
    0.09
    ä¾Ŀçħ§
    0.09
    emption
    0.08
     Organisation
    0.08
    ocious
    0.08
    Activations Density 0.169%

    No Known Activations