© 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. 52479
    Prev
    Next
    INDEX
    Explanations

    people and related groups

    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
    èŀºæĹĭ
    -0.10
    èį
    -0.10
    å®ĺ
    -0.08
    æ¨Ł
    -0.08
    èij«èĬ¦
    -0.08
    posium
    -0.08
    èįĨ
    -0.08
    åĨįçĶŁ
    -0.08
    زÙĬد
    -0.08
    IDES
    -0.08
    POSITIVE LOGITS
    å¿Ĵ
    0.09
     tá»Ļc
    0.09
    æĻ®æŁ¥
    0.09
    以人æ°ij
    0.09
    çĺ¼
    0.09
    èİĨ
    0.08
    ä½łå¥½
    0.08
    ç²¹
    0.08
    æ°ijéĹ´
    0.08
    åĬ¨åijĺ
    0.08
    Activations Density 0.064%

    No Known Activations