© 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. 57511
    Prev
    Next
    INDEX
    Explanations

    adverse events or outcomes

    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
    åIJŀ
    -0.08
    å±ł
    -0.08
    è¾¹
    -0.08
    çĨŁæĤī
    -0.08
    usp
    -0.07
    tern
    -0.07
    æĮ¥
    -0.07
     weir
    -0.07
     Sail
    -0.07
    riz
    -0.07
    POSITIVE LOGITS
    çļĦåıijçĶŁ
    0.11
    çİĩ
    0.11
     rates
    0.10
    ánh
    0.10
     Rates
    0.10
    äºĭ件
    0.10
    åıijçĶµ
    0.10
    çİĩè¾¾
    0.10
    åħ¨éĿ¢åıijå±ķ
    0.09
    åħ¬åħĥåīį
    0.09
    Activations Density 0.896%

    No Known Activations