© 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. 51086
    Prev
    Next
    INDEX
    Explanations

    judicial/judiciary related terms

    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
    åŃIJéĩĮ
    -0.11
    cha
    -0.08
    ood
    -0.08
    åħļå§Ķ
    -0.08
    RuntimeObject
    -0.08
     rid
    -0.08
     PET
    -0.08
    ìĶ¨
    -0.08
    ord
    -0.08
    PET
    -0.08
    POSITIVE LOGITS
    urally
    0.11
    ly
    0.10
    çķĮ第ä¸Ģ
    0.10
    çĽĽå®´
    0.10
    mente
    0.10
    icious
    0.10
    éĻ¢éķ¿
    0.09
    为æ°ij
    0.09
    radius
    0.09
    yla
    0.09
    Activations Density 0.010%

    No Known Activations