© 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. 57677
    Prev
    Next
    INDEX
    Explanations

    body weight, builders, mass, fluids

    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
    çĶŁæľº
    -0.09
    ivant
    -0.09
    ipi
    -0.08
    sword
    -0.08
    èĢ³æľµ
    -0.08
    è¸ŀ
    -0.08
    sid
    -0.08
    çļĦèĦ¸
    -0.08
    å¸Ń
    -0.08
    佯
    -0.08
    POSITIVE LOGITS
    ê°IJ
    0.09
    åħ¨è¦ĨçĽĸ
    0.09
    离ä¸įå¼Ģ
    0.09
    é¨
    0.09
    builders
    0.09
    çĸı导
    0.08
    ream
    0.08
    SHOT
    0.08
    èĥ½åĬĽåĴĮ
    0.08
    tre
    0.08
    Activations Density 0.043%

    No Known Activations