© 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. 21744
    Prev
    Next
    INDEX
    Explanations

    technical or code snippets

    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
    æį»
    -0.09
    çłĶ究æīĢ
    -0.09
    åIJĥäºı
    -0.08
    pei
    -0.08
    æĬ¹
    -0.08
    åĺĮ
    -0.08
    ÐĺÐĿ
    -0.08
    èĢģçĻ¾å§ĵ
    -0.08
    æĢ»éĺŁ
    -0.08
    åĹī
    -0.08
    POSITIVE LOGITS
    é£İéĻ©ç®¡çIJĨ
    0.12
    御
    0.09
    åIJĮä¸ļ
    0.09
    Tier
    0.09
    ARB
    0.09
    åĪ°æľĢåIJİ
    0.09
    å±Ĥ次
    0.08
    LEAR
    0.08
    unc
    0.08
    åij¨è½¬
    0.08
    Activations Density 0.106%

    No Known Activations