© 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. 20349
    Prev
    Next
    INDEX
    Explanations

    lacks, not enough, worth mentioning

    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
    åij½ä¸Ń
    -0.09
    ä¿Ŀå®Ī
    -0.08
     wing
    -0.08
    cellent
    -0.08
    è¿Ļå¥Ĺ
    -0.08
    lies
    -0.08
     certain
    -0.07
    ä¸Ģ侧
    -0.07
     Tong
    -0.07
    åģı
    -0.07
    POSITIVE LOGITS
    åĵªæĢķæĺ¯
    0.12
    åĵªæĢķ
    0.12
    æľīä»»ä½ķ
    0.12
    åħ´å¥ĭ
    0.11
     ÑģобÑģÑĤвенно
    0.11
     سÙĪÙī
    0.11
    éĻ¤éĿŀ
    0.11
    éĻ¤äºĨ
    0.10
    ä½ķãģĭ
    0.10
    åįģ大
    0.10
    Activations Density 0.054%

    No Known Activations