© 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. 18248
    Prev
    Next
    INDEX
    Explanations

    making things easier

    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
    樯
    -0.09
    èļķ
    -0.09
    immel
    -0.09
    _contin
    -0.09
    ç½¢
    -0.08
    è¯ĥ
    -0.08
    ç½´
    -0.08
    ä¾Ľæļĸ
    -0.08
    çĶŁäº§èĥ½åĬĽ
    -0.08
    åĨ²
    -0.08
    POSITIVE LOGITS
    便åĪ©
    0.11
     easier
    0.11
    便æį·
    0.11
    æĸ¹ä¾¿
    0.10
    ç®ĢåĮĸ
    0.10
    è¾ħåĬ©
    0.09
    èħ°
    0.09
    æĽ´å®¹æĺĵ
    0.09
    æľīæīĢ帮åĬ©
    0.09
     ease
    0.09
    Activations Density 0.107%

    No Known Activations