© 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. 11842
    Prev
    Next
    INDEX
    Explanations

    pivot | swing | hinged

    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
    åĿIJæłĩ
    -0.21
    åĨħç§ij
    -0.20
    inventory
    -0.20
    è¿·
    -0.20
    çľł
    -0.19
    åºĵåŃĺ
    -0.19
    éĢļä¿¡
    -0.18
    ernet
    -0.18
     Herm
    -0.18
     nar
    -0.18
    POSITIVE LOGITS
    èĩĤ
    0.28
    æĿłæĿĨ
    0.28
     swings
    0.27
    平衡
    0.27
     swing
    0.27
     swinging
    0.27
    -arm
    0.27
    ç¿ĺ
    0.26
    æĴ¬
    0.25
     Coff
    0.24
    Activations Density 0.156%

    No Known Activations