© 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. 17894
    Prev
    Next
    INDEX
    Explanations

    distance between two points

    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
     Benson
    -0.10
    Expose
    -0.09
    æĭ¼éŁ³
    -0.08
    é¢Ħå®ļ
    -0.08
    ä¾£
    -0.08
    BSD
    -0.08
    onga
    -0.08
     diced
    -0.08
    nga
    -0.07
    recogn
    -0.07
    POSITIVE LOGITS
     distances
    0.11
    çļĦè·Ŀ离
    0.10
    _DISTANCE
    0.10
     Distance
    0.10
    .distance
    0.09
    StreamReader
    0.09
    éģį
    0.09
    INTR
    0.09
    distance
    0.09
    åįĹæµ·
    0.09
    Activations Density 0.025%

    No Known Activations