© 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. 8755
    Prev
    Next
    INDEX
    Explanations

    make sure

    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
    åĩ«
    -0.09
    gs
    -0.09
    wen
    -0.09
    æĺ¾çİ°
    -0.09
    èIJ½åľ°
    -0.09
    åı¦è¡Į
    -0.08
    ·»
    -0.08
    _UNS
    -0.08
    沫
    -0.08
    è¿Ļæīįæĺ¯
    -0.08
    POSITIVE LOGITS
    oyal
    0.10
    åĩĨ
    0.10
     sure
    0.09
    onica
    0.08
    åĬªåĬĽ
    0.08
    çļİ
    0.08
    ITT
    0.08
    ived
    0.08
    enty
    0.08
    å¾Ĺå¤ļ
    0.08
    Activations Density 0.025%

    No Known Activations