© 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. 51901
    Prev
    Next
    INDEX
    Explanations

    from sources and origins

    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
    çıī
    -0.10
    éĢ¶
    -0.09
    apas
    -0.09
    å°ıçĶ·åŃ©
    -0.09
    訾
    -0.09
    ä¸ĢåĪĩéĥ½
    -0.08
    çĮ·
    -0.08
    ì·¨
    -0.08
    æĬĹ
    -0.08
    elian
    -0.08
    POSITIVE LOGITS
    ä»»ä½ķä¸Ģ个
    0.10
    à¹ĥà¸Ķ
    0.09
    itle
    0.09
     شب
    0.09
    ä»»ä½ķ
    0.09
     ANY
    0.09
     any
    0.08
    iaux
    0.08
    èĮ¬
    0.08
    çħ§æł·
    0.08
    Activations Density 0.101%

    No Known Activations