© 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. 17864
    Prev
    Next
    INDEX
    Explanations

    SSD, GPU, state, Sword

    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
    umm
    -0.10
    èĮ¸
    -0.09
    å½±è§Ĩ
    -0.09
    追éĢIJ
    -0.09
    ance
    -0.08
     cele
    -0.08
    sticks
    -0.08
    NBC
    -0.08
     mainland
    -0.08
    åIJ¬å¾Ĺ
    -0.08
    POSITIVE LOGITS
    crow
    0.09
    们
    0.09
    aney
    0.09
    iasi
    0.09
    Powered
    0.09
    çĢį
    0.09
    idge
    0.08
    .Batch
    0.08
    rov
    0.08
    è¡¢
    0.08
    Activations Density 0.014%

    No Known Activations