© 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. 51539
    Prev
    Next
    INDEX
    Explanations

    at the

    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
    ëĦĪ
    -0.09
    èĢķåľ°
    -0.09
    holm
    -0.08
     ÐĴаÑģ
    -0.08
    æĵ¦
    -0.08
    RuntimeObject
    -0.08
    aroo
    -0.08
     Sofa
    -0.08
    èĤĺ
    -0.08
    kowski
    -0.08
    POSITIVE LOGITS
    ä¸ĢäºĮ
    0.09
    ä¸Ģè§Ī
    0.09
    ä¸Ģç³»åĪĹ
    0.09
    å¾Ĺèµ·
    0.09
    åĪ°ä½į
    0.08
    ä¸Ĭå¹´
    0.08
    åĪ°è¿ĻéĩĮ
    0.08
    大大æıIJé«ĺ
    0.08
    \:
    0.08
    寤
    0.08
    Activations Density 0.075%

    No Known Activations