© 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. 34804
    Prev
    Next
    INDEX
    Explanations

    owned, purchased, over, present

    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
    eve
    -0.10
    ota
    -0.09
    otes
    -0.08
    éĶĢåĶ®äººåijĺ
    -0.08
    .Raise
    -0.08
    è¾į
    -0.08
    cow
    -0.08
    ç³Ĭ
    -0.08
    循
    -0.08
    amble
    -0.08
    POSITIVE LOGITS
    å¾ģ
    0.10
    enville
    0.09
    ellen
    0.09
    æij¸
    0.09
    çĶ¨äºİ
    0.09
    .partial
    0.09
     Owned
    0.09
    涵
    0.09
    (owner
    0.09
    æīĢæľīæĿĥ
    0.08
    Activations Density 0.036%

    No Known Activations