© 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. 8084
    Prev
    Next
    INDEX
    Explanations

    U.S. citations

    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
    åĿ¦
    -0.11
    大ä¼Ĺ
    -0.08
    \<^
    -0.08
    è´¿
    -0.08
    -mf
    -0.08
    è°ħ
    -0.08
    á¸ĥ
    -0.08
    广大
    -0.08
    ç»Ļèĩªå·±
    -0.08
    èĭ¾
    -0.08
    POSITIVE LOGITS
    _tac
    0.10
    èĪħ
    0.09
    ฯ
    0.08
    æİī
    0.08
    éĴł
    0.08
    âĺ°
    0.08
    ophile
    0.08
    ermen
    0.08
     nou
    0.08
    èĦĬ
    0.08
    Activations Density 0.066%

    No Known Activations