© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 61353
    Prev
    Next
    INDEX
    Explanations

    current state or stage

    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
    åīįæľŁ
    -0.11
    åľ°æ®µ
    -0.09
    åīįéĿ¢
    -0.09
    æĬĬæĪij
    -0.09
    æ¹¾åĮº
    -0.09
    _fraction
    -0.09
    å¹³æĹ¶
    -0.09
    身价
    -0.08
    åİ¥
    -0.08
    è¿Ļ次
    -0.08
    POSITIVE LOGITS
    读åIJİ
    0.10
    奴
    0.09
    /current
    0.09
    erland
    0.09
    sume
    0.08
    æĿī
    0.08
    å¿¿
    0.08
    aos
    0.08
    verte
    0.08
    edy
    0.08
    Activations Density 0.130%

    No Known Activations