© 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. 49200
    Prev
    Next
    INDEX
    Explanations

    candidly, Candidatus, Candida, candidemia

    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
    halb
    -0.10
    çªŁ
    -0.09
    gae
    -0.08
     Tibet
    -0.08
    iminal
    -0.08
    osoph
    -0.08
    æĸ¤
    -0.08
    å£ģåŀĴ
    -0.08
    ein
    -0.08
     contend
    -0.08
    POSITIVE LOGITS
    ly
    0.14
    ness
    0.13
    åĴĮæĶ¯æĮģ
    0.10
    NESS
    0.10
    ../../../
    0.10
    ../../
    0.09
    åħ¨è¿ĩç¨ĭ
    0.09
     Äijáo
    0.09
    伺
    0.09
    åħ¨åİ¿
    0.09
    Activations Density 0.007%

    No Known Activations