© 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. 36774
    Prev
    Next
    INDEX
    Explanations

    and around

    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
    ç¨ļ
    -0.11
    çĿ½
    -0.10
    æĻ°
    -0.09
    aram
    -0.09
    iage
    -0.09
    ARAM
    -0.09
    StreamWriter
    -0.09
    忽
    -0.08
    åīįè¿Ľ
    -0.08
     MU
    -0.08
    POSITIVE LOGITS
    enberg
    0.09
    æ»´
    0.08
    æ²Ľ
    0.08
    å¸Ĥãģ®
    0.08
    uros
    0.08
    个æľĪ
    0.08
    uous
    0.08
    è£Ĩ
    0.08
    å«£
    0.08
    以å¤ĸ
    0.08
    Activations Density 0.038%

    No Known Activations