© 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. 61925
    Prev
    Next
    INDEX
    Explanations

    black hole and neutron star

    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
    èµ·ä¼ı
    -0.09
    éĽªèĬ±
    -0.09
    è¹Ħ
    -0.08
    å¤įåħ´
    -0.08
    plib
    -0.08
     ale
    -0.08
    被æ·ĺæ±°
    -0.08
    éļĭ
    -0.08
    spaces
    -0.08
    殳
    -0.08
    POSITIVE LOGITS
    é»ijæ´ŀ
    0.11
    æ®Ħ
    0.10
    .Pod
    0.09
    éŨåīį
    0.09
    izzo
    0.09
    åĴ§
    0.09
    麻辣
    0.09
    峡
    0.09
    ä¸Ģ年级
    0.08
    æĽľ
    0.08
    Activations Density 0.071%

    No Known Activations