© 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. 61537
    Prev
    Next
    INDEX
    Explanations

    web addresses ending in .com

    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
    ä¼
    -0.09
    thic
    -0.09
     erg
    -0.09
    éĩį伤
    -0.09
    SqlConnection
    -0.08
    è¶Ĭ好
    -0.08
    è¦ģåѦä¼ļ
    -0.08
    iphy
    -0.08
    åѦä¼ļ
    -0.08
    çīĤ
    -0.08
    POSITIVE LOGITS
    èī¯å¿ĥ
    0.09
    翳
    0.09
    visibility
    0.09
    æīĵåĩº
    0.08
    çĦ
    0.08
     Nicholson
    0.08
    од
    0.08
     Visibility
    0.08
     furnished
    0.08
    欢åĸľ
    0.08
    Activations Density 0.004%

    No Known Activations