© 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. 37787
    Prev
    Next
    INDEX
    Explanations

    names like Helen, Paul, Sarah

    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
    æ¦Ĩ
    -0.09
    缮åīįåĽ½åĨħ
    -0.09
    æªĶ
    -0.08
    CID
    -0.08
    èIJ½åı¶
    -0.08
    ield
    -0.08
    å®ļä½į
    -0.07
    çİĩè¾¾åĪ°
    -0.07
    alyzer
    -0.07
    åĿł
    -0.07
    POSITIVE LOGITS
    ä¸Ģèµ·æĿ¥
    0.10
    å¼ķ
    0.10
    åľ¨ä¸ĢæĹģ
    0.10
    åIJĮä¼´
    0.09
    /compiler
    0.09
    éĤ£è¾¹
    0.08
    Todd
    0.08
    redni
    0.08
    导å¸Ī
    0.08
    æĬķæłĩ
    0.08
    Activations Density 0.046%

    No Known Activations