© 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. 35917
    Prev
    Next
    INDEX
    Explanations

    efficacy and effectiveness

    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
    çļĦéľĢæ±Ĥ
    -0.09
    æĶ¾å¼Ģ
    -0.09
    çļĦåĬªåĬĽ
    -0.09
    çļĦæĪIJéķ¿
    -0.08
    ูล
    -0.08
    åĬ¿å¿ħ
    -0.08
    游åĩ»
    -0.08
    åIJĪçIJĨæĢ§
    -0.08
     fé
    -0.08
    æĻºåĬĽ
    -0.08
    POSITIVE LOGITS
    æķĪæŀľ
    0.16
     effectiveness
    0.15
     efficacy
    0.15
    å®ŀæķĪ
    0.13
    çĸĹæķĪ
    0.12
    çļĦæķĪæŀľ
    0.12
    æķĪæŀľåĽ¾
    0.12
     ÑįÑĦÑĦекÑĤив
    0.11
    æķĪåĬĽ
    0.11
    æľīæķĪæĢ§
    0.11
    Activations Density 0.359%

    No Known Activations