© 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. 56533
    Prev
    Next
    INDEX
    Explanations

    making or causing consequence

    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
    kus
    -0.09
    ä¸įçĦ¶
    -0.09
    ä¸įèµ·
    -0.09
     Cyr
    -0.08
    好äºĨ
    -0.08
    zelf
    -0.08
    好好
    -0.08
    红æĺŁ
    -0.08
    çļĦä¸Ģ
    -0.08
    enburg
    -0.08
    POSITIVE LOGITS
    使åħ¶
    0.12
    çĦ¶æĺ¯
    0.10
    åıĪä¸Ģ次
    0.10
    çĥĻ
    0.10
    对åħ¶
    0.10
    ogn
    0.10
    opr
    0.09
    ç¬ĶèĢħ
    0.09
    é¢ĺ主
    0.09
     presumably
    0.09
    Activations Density 0.233%

    No Known Activations