© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 16252
    Prev
    Next
    INDEX
    Explanations

    movement and political movements

    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
    å¤ļå¹´æĿ¥
    -0.22
    ä¹¡åľŁ
    -0.21
    åĶ®åIJİ
    -0.21
    çļĩ家
    -0.21
    å¤ļå¹´
    -0.20
    åIJ¬åĬĽ
    -0.20
    çłĶåıijä¸Ńå¿ĥ
    -0.20
    äºĭæķħ
    -0.20
     Overse
    -0.20
    çľģæķĻèĤ²åİħ
    -0.20
    POSITIVE LOGITS
     movement
    0.27
     mobil
    0.25
     movements
    0.23
    Movement
    0.21
    .mov
    0.21
     Movement
    0.21
     momentum
    0.20
    åĽ¢ä½ĵ
    0.20
    箪
    0.20
     movimiento
    0.19
    Activations Density 0.024%

    No Known Activations