© 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. 52522
    Prev
    Next
    INDEX
    Explanations

    credible, believable, plausible

    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
    ÙĬرÙĬ
    -0.10
    èIJ½ãģ¡
    -0.09
    lander
    -0.08
    æł¹æľ¬
    -0.08
    LEN
    -0.08
    YC
    -0.08
    好å¤Ħ
    -0.08
    åŀĤ
    -0.08
    veled
    -0.08
    好è¯Ħ
    -0.08
    POSITIVE LOGITS
    ä¸įäºĨ
    0.11
    odata
    0.09
    -minded
    0.09
    ä¸İåIJ¦
    0.09
    ony
    0.09
    erto
    0.09
    å·²ä¹ħçļĦ
    0.09
    oad
    0.08
    åIJĦä½į
    0.08
    1
    0.08
    Activations Density 0.009%

    No Known Activations