© 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. 4380
    Prev
    Next
    INDEX
    Explanations

    obverse, interproximal, contact surface, broken down

    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
    ogens
    -0.09
    æĹłåģ¿
    -0.08
    æ³Ĭ
    -0.08
    æ·Ļ
    -0.08
    çŃīçĿĢ
    -0.08
    (EC
    -0.08
    ç´IJ
    -0.08
    pitch
    -0.08
    opers
    -0.08
    马åĬĽ
    -0.08
    POSITIVE LOGITS
    dit
    0.09
    ä¸Ģ声
    0.09
    å²Ĺ
    0.09
    FIT
    0.09
     Halo
    0.08
    æ¨Ł
    0.08
    åIJĦè¡Į
    0.08
    社ä¼ļæķĪçĽĬ
    0.08
    è°
    0.08
    éľģ
    0.08
    Activations Density 0.052%

    No Known Activations