© 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
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 1341
    Prev
    Next
    INDEX
    Explanations

    transparency

    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
    iard
    -0.09
    åŀ
    -0.09
    æĶ¶ç´§
    -0.08
    dsl
    -0.08
    _shortcode
    -0.08
    åĩºåĬ¨
    -0.08
    å¼Ģå·¥
    -0.08
    åįķ身
    -0.08
     Bearing
    -0.08
    roid
    -0.08
    POSITIVE LOGITS
    éĢıæĺİ
    0.14
    -bodied
    0.10
    çĽ²
    0.09
    让人们
    0.09
    /trans
    0.09
    (ins
    0.09
     transparency
    0.09
    HostName
    0.09
    æ¾Ī
    0.09
    uxe
    0.09
    Activations Density 0.049%

    No Known Activations