© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37405
    Prev
    Next
    INDEX
    Explanations

    for

    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
    åĨĽäºĭ
    -0.08
    å¯Įæľī
    -0.08
    è¾Ļ
    -0.08
    ä½Ĩä»į
    -0.08
    ä¼IJ
    -0.07
    å½ĵçĦ¶
    -0.07
    åĨĽ
    -0.07
    ож
    -0.07
    çºł
    -0.07
    bounding
    -0.07
    POSITIVE LOGITS
    çĺ´
    0.10
    .ali
    0.10
    åĪ«è¯´
    0.10
    ãģ¶ãĤĬ
    0.09
    æĺ¯è°ģ
    0.09
    ä¸ĸçķĮ第ä¸Ģ
    0.09
    TOT
    0.08
    å¾Īæľīåı¯èĥ½
    0.08
    ä¸įçĦ¶
    0.08
    å¾Īåı¯èĥ½
    0.08
    Activations Density 0.030%

    No Known Activations