© 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. 20884
    Prev
    Next
    INDEX
    Explanations

    century gothic font

    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
    enstein
    -0.10
    åĪ°è¿ĻéĩĮ
    -0.09
    åįĥéĩĮ
    -0.09
     Levi
    -0.09
    ä¸įè¿ľå¤Ħ
    -0.08
    èĬĿ
    -0.08
    庶
    -0.08
    èŀ½
    -0.08
    ×Ļ׼
    -0.08
    æĸ°éĹ»ä¸Ńå¿ĥ
    -0.08
    POSITIVE LOGITS
    wide
    0.09
    thon
    0.09
    aring
    0.09
    geist
    0.08
    hood
    0.08
    åĪĨæł¡
    0.08
    eon
    0.08
    éĢļãĤĬ
    0.08
    ä¹İ
    0.08
    éĻĽ
    0.08
    Activations Density 0.017%

    No Known Activations