© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 848
    Prev
    Next
    INDEX
    Explanations

    firefighter

    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
    Negative Logits
    没åħ³ç³»
    -0.11
    累累
    -0.11
    èĬľ
    -0.10
    å·²ä¹ħçļĦ
    -0.10
    ড
    -0.10
    æĪij以为
    -0.10
    ussen
    -0.10
    éķĴ
    -0.10
    å°±è¿ŀ
    -0.10
    好äºĭ
    -0.09
    POSITIVE LOGITS
    unes
    0.09
    çĶ¨åĵģ
    0.08
    _BUSY
    0.08
    æĬij
    0.08
     union
    0.08
    ein
    0.08
    éĺŁåijĺ
    0.08
    aru
    0.08
    éļĬ
    0.08
    union
    0.08
    Activations Density 0.012%

    No Known Activations