© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38188
    Prev
    Next
    INDEX
    Explanations

    movement or 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
    丧
    -0.10
     Publish
    -0.10
    çĭİ
    -0.10
    缴åįĩ
    -0.09
    [ID
    -0.09
    ä¸Ģæľ¬
    -0.09
    åij¨æľ«
    -0.09
    å±ĭ顶
    -0.09
     hå
    -0.09
    è°¯
    -0.09
    POSITIVE LOGITS
     movement
    0.17
     motion
    0.16
    è¿IJåĬ¨
    0.16
     движ
    0.15
    åĭķãģį
    0.15
    åīįè¿Ľ
    0.15
    movement
    0.15
    motion
    0.14
    _motion
    0.14
     движениÑı
    0.14
    Activations Density 0.101%

    No Known Activations