© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12294
    Prev
    Next
    INDEX
    Explanations

    movement of physical objects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
     Witness
    -0.20
    èĦ
    -0.20
    idor
    -0.20
    kees
    -0.20
    æµ£
    -0.19
    æݼ
    -0.19
    erson
    -0.19
    obic
    -0.18
    çĶŁæ´»çݯå¢ĥ
    -0.18
    æŸ
    -0.18
    POSITIVE LOGITS
     movements
    0.29
    é¾ĻéŨ
    0.26
    精度
    0.25
    æĵį纵
    0.24
    движ
    0.24
    è¿IJåĬ¨
    0.23
    è¾į
    0.23
    æľºæŀĦ
    0.23
     movement
    0.23
    mov
    0.22
    Activations Density 0.115%

    No Known Activations