© 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. 11831
    Prev
    Next
    INDEX
    Explanations

    renowned and associated nouns

    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
    sst
    -0.08
    æ®ĩ
    -0.08
    çľ
    -0.08
    èĻ«
    -0.08
    éĥ½ä¸įä¼ļ
    -0.08
    è§ģè¯ģ
    -0.08
    çĿĢå®ŀ
    -0.08
    pool
    -0.08
    edes
    -0.07
    å°¤åħ¶æĺ¯åľ¨
    -0.07
    POSITIVE LOGITS
    inaire
    0.12
    人士
    0.11
    emente
    0.10
    ÑĪим
    0.10
    æ²»
    0.10
    uxe
    0.09
    å©¿
    0.09
    çĴIJ
    0.09
    ety
    0.09
    èĢħçļĦ
    0.09
    Activations Density 0.015%

    No Known Activations