© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 57914
    Prev
    Next
    INDEX
    Explanations

    economical worthwhile sense effective justify

    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
    éĺħ
    -0.09
    æīĺ
    -0.09
    ä¸Ģ个æĺŁæľŁ
    -0.09
    enser
    -0.09
    ä¹ĸ
    -0.09
    æįį
    -0.08
    é£İæł¼
    -0.08
    è¹ij
    -0.08
    æľĢåħ³éĶ®çļĦ
    -0.08
    å¯Ĥå¯ŀ
    -0.08
    POSITIVE LOGITS
    åĪĴç®Ĺ
    0.18
    è¿ĺä¸įå¦Ĥ
    0.17
    æĪIJæľ¬
    0.13
    åı¯è¡Į
    0.12
     cost
    0.12
     economics
    0.12
     вÑĭгод
    0.11
    ç»ıæµİ
    0.11
    ç»ıæµİæķĪçĽĬ
    0.11
     Cost
    0.11
    Activations Density 0.122%

    No Known Activations