© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51006
    Prev
    Next
    INDEX
    Explanations

    Beethoven, forge, on

    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
    å¹»æĥ³
    -0.11
    Ùħرا
    -0.09
    è¯Ļ
    -0.09
    .ali
    -0.09
    kers
    -0.09
    éŃģ
    -0.09
    å¾ĹçĽĬ
    -0.09
    infinity
    -0.09
    çĤ¹å¤ļ
    -0.09
     drafts
    -0.09
    POSITIVE LOGITS
    å°¼äºļ
    0.10
    åIJĿ
    0.08
    é²ģ
    0.08
    nz
    0.08
    åºĶåıĬæŶ
    0.08
    æ»ĵ
    0.08
    æĺĶ
    0.08
    éĴ¿
    0.07
    ä»ĭ
    0.07
    æ¯Ľ
    0.07
    Activations Density 0.004%

    No Known Activations