© 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. 62566
    Prev
    Next
    INDEX
    Explanations

    technical, chart, trend, indicators

    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
    unar
    -0.09
    æ¯Ķäºļ
    -0.09
    å¢ŀåĢ¼
    -0.09
    arma
    -0.09
    çĶ¨æĪ·æıIJä¾Ľ
    -0.09
    åĦĨ
    -0.09
    ç»ijæŀ¶
    -0.09
    иÑĢа
    -0.09
    çĤ¹ç¼Ģ
    -0.08
    åŀ«
    -0.08
    POSITIVE LOGITS
    ç¶ļãģį
    0.09
     exped
    0.09
     вÑģ
    0.09
    jej
    0.08
    æıĴ
    0.08
    åIJĥåĪ°
    0.08
    èĭ«
    0.08
     Wor
    0.08
    æ¢ħ西
    0.08
     IDs
    0.08
    Activations Density 0.051%

    No Known Activations