© 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. 1094
    Prev
    Next
    INDEX
    Explanations

    DDR RAM memory

    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
    æĮĽ
    -0.10
    æ°´æºIJ
    -0.09
    SPA
    -0.09
    ĶåĽŀ
    -0.09
    çľĩ
    -0.08
    æľĹ
    -0.08
    icator
    -0.08
    åł¡
    -0.08
    éĴĬ
    -0.08
    ç¥IJ
    -0.08
    POSITIVE LOGITS
    ç®´
    0.09
    溱
    0.09
    容éĩı
    0.09
    ós
    0.09
    аÑĤÑĥÑĢ
    0.09
    çĵ¶é¢Ī
    0.09
     RAM
    0.09
    æĴ¤éĶĢ
    0.09
    .Cart
    0.09
    åıĺåĬ¨
    0.09
    Activations Density 0.062%

    No Known Activations