© 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. 36740
    Prev
    Next
    INDEX
    Explanations

    conjunctions like and or

    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
    ä¸į幸
    -0.09
    æ§
    -0.08
    éĶĢ
    -0.08
     irritating
    -0.08
    iry
    -0.08
    帻
    -0.08
    åĬ¡å®ŀ
    -0.08
     Rid
    -0.08
    classname
    -0.07
    æĹ¥åŃIJ
    -0.07
    POSITIVE LOGITS
    udes
    0.09
    ÂŃs
    0.09
    çıij
    0.09
    ноÑģÑĤей
    0.09
    æ»ĵ
    0.09
    éľģ
    0.09
    请æķĻ
    0.08
    åĨ¶çĤ¼
    0.08
    [s
    0.08
    庫
    0.08
    Activations Density 0.213%

    No Known Activations