© 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. 7649
    Prev
    Next
    INDEX
    Explanations

    feedback and suggestions

    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¤Ĵ
    -0.09
    craper
    -0.09
    èĩ´æķ¬
    -0.09
    æ²Į
    -0.09
    åľ¨åĽ½åĨħ
    -0.09
    /scripts
    -0.09
     اÙĦØŃاÙĦ
    -0.08
    ÑĪа
    -0.08
    жÑĥ
    -0.08
    .today
    -0.08
    POSITIVE LOGITS
     feedback
    0.15
    åıįé¦Ī
    0.14
    æĮĩçĤ¹
    0.13
    æĦıè§ģ
    0.12
    Feedback
    0.12
    æĮĩåĩº
    0.12
     Feedback
    0.12
    feedback
    0.12
    æĦıè§ģåıįé¦Ī
    0.11
     constructive
    0.11
    Activations Density 0.119%

    No Known Activations