© 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. 53536
    Prev
    Next
    INDEX
    Explanations

    forth and back motion

    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
    æºı
    -0.10
    é«ĺçŃī
    -0.09
    TERS
    -0.09
    èŀį
    -0.09
    æ®ļ
    -0.09
    åIJįæł¡
    -0.09
    临
    -0.09
    æĭĨ
    -0.09
    .Sdk
    -0.09
     spots
    -0.09
    POSITIVE LOGITS
     движениÑı
    0.15
    æĿ¥åĽŀ
    0.14
    åĭķãģį
    0.13
    å¹ħ度
    0.13
     motions
    0.13
     motion
    0.13
    è¿IJåĬ¨
    0.13
     movement
    0.13
    æĻĥ
    0.13
     movements
    0.12
    Activations Density 0.166%

    No Known Activations