© 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. 33256
    Prev
    Next
    INDEX
    Explanations

    disposition, elimination, half-life

    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
    åIJ®
    -0.10
    èĺ¸
    -0.10
    èįī
    -0.09
    CSR
    -0.09
    æĮ¯ãĤĬ
    -0.09
    åħ¬çĶ¨
    -0.09
     Thornton
    -0.08
    ç´§åĩij
    -0.08
    æ²Ļæ¼ł
    -0.08
    æ´½
    -0.08
    POSITIVE LOGITS
    æ®ĺ
    0.10
    èIJ½åľ°
    0.10
    æ¸ħéĻ¤
    0.10
    æŶæķĪ
    0.09
    åģľçķĻ
    0.09
    yle
    0.09
    imore
    0.09
    çĬģ
    0.09
    æ®ĭ
    0.09
    å¾Īå¿«
    0.09
    Activations Density 0.521%

    No Known Activations