© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38199
    Prev
    Next
    INDEX
    Explanations

    registered trademark or copyright

    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
    _INV
    -0.09
    åĪij
    -0.09
    溱
    -0.08
    æĭ¦æĪª
    -0.08
     CURLOPT
    -0.08
    港
    -0.08
    골
    -0.08
    Destructor
    -0.08
     Dickinson
    -0.08
    解æĶ¾
    -0.08
    POSITIVE LOGITS
    веÑĩ
    0.10
    åį§
    0.10
     trademarks
    0.09
     fer
    0.09
    çŃ¹
    0.09
    çĭŃ
    0.09
    躺
    0.09
    ibraries
    0.09
    å¤ļæĸ¹
    0.09
    _reserved
    0.08
    Activations Density 0.013%

    No Known Activations