© 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. 2475
    Prev
    Next
    INDEX
    Explanations

    interactive computing devices and data

    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
    æĪª
    -0.10
    士
    -0.09
    çŁ¥ä¹İ
    -0.09
    çĿģ
    -0.09
    å¿ĥæĢģ
    -0.09
    åĬŁèĥ½æĢ§
    -0.08
    ìĤŃ
    -0.08
    çĶŁæĢķ
    -0.08
     milit
    -0.08
    说åĩºæĿ¥
    -0.08
    POSITIVE LOGITS
    æľīæĦıæĢĿçļĦ
    0.11
    cheid
    0.10
    æľī趣
    0.10
    çī©ä»¶
    0.09
    èĩªåıij
    0.09
    indle
    0.08
    æµ®çİ°
    0.08
    orsche
    0.08
    让人们
    0.08
    stalk
    0.08
    Activations Density 0.173%

    No Known Activations