© 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. 8132
    Prev
    Next
    INDEX
    Explanations

    telecom regulator or commission

    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
    æİ©
    -0.09
    éĥĬåĮº
    -0.09
    æīĴ
    -0.09
    ä¸įéĢļ
    -0.08
    borrow
    -0.08
    æݥ轨
    -0.08
    èļģ
    -0.08
    çĶŁæ´»çݯå¢ĥ
    -0.08
    heart
    -0.08
    bern
    -0.08
    POSITIVE LOGITS
    IPH
    0.09
    ç¿
    0.09
    IID
    0.09
    éĴ¿
    0.09
    _ie
    0.09
     DÆ°Æ¡ng
    0.09
    çĭ¬è§Ĵ
    0.08
    é¼ĵèĪŀ
    0.08
    æķ´é¡¿
    0.08
    ancements
    0.08
    Activations Density 0.082%

    No Known Activations